-
H. B. Ammar and M. Tokic, Reinforcement Learning using a Physical Robot, in Proceedings of the Teaching Machine Learning Workshop at the International Conference of Machine Learning (ICML), Edinburg, Scotland, 2012.
@inproceedings{Haitham2012d, address={Edinburg, Scotland},
author={Haitham Bou Ammar and Michel Tokic},
booktitle={Proceedings of the Teaching Machine Learning Workshop at the International Conference of Machine Learning (ICML)},
title={Reinforcement Learning using a Physical Robot},
year=2012, }
-
D. Hennes, D. Claes, W. Meeussen, and K. Tuyls, Multi-robot collision avoidance with localization uncertainty, in Proceedings of 11th International Conference on Adaptive Agents and Multi-agent Systems (AAMAS 2012), Valencia, Spain, 2012.
@inproceedings{Hennes2012, address={Valencia, Spain},
author={Daniel Hennes and Daniel Claes and Wim Meeussen and Karl Tuyls},
booktitle={Proceedings of 11th International Conference on Adaptive Agents and Multi-agent Systems (AAMAS 2012)},
month={June},
title={Multi-robot collision avoidance with localization uncertainty},
year=2012, }
-
H. B. Ammar, M. E.Taylor, K. Tuyls, K. Driessens, and G. Weiss, Reinforcement Learning Transfer via Sparse Coding (Full Paper), in Proceedings of the eleventh conference on Autonomous Agents and Multiagent Systems (AAMAS), Valencia, Spain, 2012.
@inproceedings{Haitham2012a, address={Valencia, Spain},
author={Haitham Bou Ammar and Mathew E.Taylor and Karl Tuyls and Kurt Driessens and Gerhard Weiss},
booktitle={Proceedings of the eleventh conference on Autonomous Agents and Multiagent Systems (AAMAS)},
title={Reinforcement Learning Transfer via Sparse Coding (Full Paper)},
year=2012, }
-
H. B. Ammar, M. Kaisers, and K. Tuyls, Evolutionary Dynamics of Ant Colony Optimization, in Proceedings of the Multiagent Technology and Systems (MATES), Trier, Germany, 2012.
@inproceedings{Haitham2012c, address={Trier, Germany},
author={Haitham Bou Ammar and Michael Kaisers and Karl Tuyls},
booktitle={Proceedings of the Multiagent Technology and Systems (MATES)},
title={Evolutionary Dynamics of Ant Colony Optimization},
year=2012, }
-
S. Chen, H. B. Ammar, K. Tuyls, and G. Weiss, Transfer Learning for Bilateral Multi Issue Negotiation, in Proceedings of the Benelux Conference on Artificial Intelligence (BNAIC), Maastricht, The Netherlands, 2012.
@inproceedings{Haitham2012g, address={Maastricht, The Netherlands},
author={Siqi Chen and Haitham Bou Ammar and Karl Tuyls and Gerhard Weiss},
booktitle={Proceedings of the Benelux Conference on Artificial Intelligence (BNAIC)},
title={Transfer Learning for Bilateral Multi Issue Negotiation},
year=2012, }
-
H. B. Ammar and S. de Jong, Advocating an Application-Driven Machine Learning Curriculum, in Proceedings of the Teaching Machine Learning Workshop at the International Conference of Machine Learning (ICML), Edinburg, Scotland, 2012.
@inproceedings{Haitham2012e, address={Edinburg, Scotland},
author={Haitham Bou Ammar and Steven de Jong},
booktitle={Proceedings of the Teaching Machine Learning Workshop at the International Conference of Machine Learning (ICML)},
title={Advocating an Application-Driven Machine Learning Curriculum},
year=2012, }
-
M. Chami, H. B. Ammar, H. Voss, K. Tuyls, and G. Weiss, An Intelligent SysML-based Conceptual Design Evaluation of Mechatronic Systems, in Proceedings of the Benelux Conference on Artificial Intelligence (BNAIC), Maastricht, The Netherlands, 2012.
@inproceedings{Haitham2012h, address={Maastricht, The Netherlands},
author={Mohammad Chami and Haitham Bou Ammar and Holger Voss and Karl Tuyls and Gerhard Weiss},
booktitle={Proceedings of the Benelux Conference on Artificial Intelligence (BNAIC)},
title={An Intelligent SysML-based Conceptual Design Evaluation of Mechatronic Systems},
year=2012, }
-
H. B. Ammar, M. E. Taylor, K. Tuyls, K. Driessens, and G. Weiss, Reinforcement Learning Transfer Using a Sparse-Coded Inter-Task Mapping, in Proceedings of the Benelux Conference on Artificial Intelligence (BNAIC), Maastricht, The Netherlands, 2012.
@inproceedings{Haitham2012f, address={Maastricht, The Netherlands},
author={Haitham Bou Ammar and Matthew E. Taylor and Karl Tuyls and Kurt Driessens and Gerhard Weiss},
booktitle={Proceedings of the Benelux Conference on Artificial Intelligence (BNAIC)},
title={Reinforcement Learning Transfer Using a Sparse-Coded Inter-Task Mapping},
year=2012, }
-
H. B. Ammar, M. E. Taylor, K. Tuyls, and G. Weiss, Reinforcement Learning Transfer Using a Sparse Coded Inter-Task Mapping, in European Workshop on Multi-agent Systems (EUMAS 2011), Maastricht, The Netherlands, 2011.
@inproceedings{Haitham2011c, address={Maastricht, The Netherlands},
author={Haitham Bou Ammar and Mathew E. Taylor and Karl Tuyls and Gerhard Weiss},
booktitle={European Workshop on Multi-agent Systems (EUMAS 2011)},
month={November},
title={Reinforcement Learning Transfer Using a Sparse Coded Inter-Task Mapping},
year=2011, }
-
H. B. Ammar and M. E. Taylor, Common Subspace Transfer for Reinforcement Learning Tasks, , Vrancx, P., Grez, M., and Kundson, M., Eds., Berlin: Springer-Verlag, 2011.
@incollection{Haitham2011d, abstract={ Agents in reinforcement learning tasks may learn slowly in large or complex tasks; transfer learning is one technique to speed up learning by providing an informative prior. How to best enable transfer between tasks with different state representations and/or actions is currently an open question. This paper introduces the concept of a common task subspace, which is used to autonomously learn how two tasks are related. Experiments in two different nonlinear domains empirically show that a learned inter-state mapping can successfully be used by fitted value iteration, to (1) improving the performance of a policy learned with a fixed number of samples, and (2) reducing the time required to converge to a (near) optimal policy with unlimited samples. },
address={Berlin},
author={Haitham Bou Ammar and Matthew E. Taylor},
booktitle={Lecture Notes in Artificial Intelligence (ALA post proceedings)},
editor={Peter Vrancx and Marek Grez and Matt Kundson},
publisher={Springer-Verlag},
title={Common Subspace Transfer for Reinforcement Learning Tasks},
year=2011, }
-
S. Alers, D. Bloembergen, D. Hennes, M. Bügler, and K. Tuyls, MITRO: an augmented mobile telepresence robot with assisted control (Demo), in Proc. of 9th European Workshop on Multi-agent Systems (EUMAS 2011), 2011.
@inproceedings{Alers2011b,
author={Sjriek Alers and Daan Bloembergen and Daniel Hennes and Max B{\"{u}}gler and Karl Tuyls},
booktitle={Proc. of 9th European Workshop on Multi-agent Systems (EUMAS 2011)},
title={MITRO: an augmented mobile telepresence robot with assisted control (Demo)},
url={http://www.flowermountains.nl/pub/Alers2011b.pdf},
year=2011, }
-
D. Bloembergen, M. Kaisers, and K. Tuyls, Empirical and Theoretical Support for Leniency in Cooperative Games (Extended abstract), in Proc. of 10th Intl. Conf. on Autonomous Agents and Multiagent Systems (AAMAS 2011), 2011, pp. 1105-1106.
@inproceedings{Bloembergen2011,
author={Daan Bloembergen and Michael Kaisers and Karl Tuyls},
booktitle={Proc. of 10th Intl. Conf. on Autonomous Agents and Multiagent Systems (AAMAS 2011)},
editor={Tumor and Yolum and Sonenberg and Stone},
pages={1105--1106},
publisher={International Foundation for AAMAS},
title={Empirical and Theoretical Support for Leniency in Cooperative Games (Extended abstract)},
url={http://www.flowermountains.nl/pub/Bloembergen2011.pdf},
year=2011, }
-
H. B. Ammar and M. E. Taylor, Common Subspace Transfer for Reinforcement Learning Tasks, in Proceedings of the AAMAS 2011 Workshop on Adaptive Learning Agents and Multi-agent Systems (ALA 2011), Taipei, Taiwan, 2011.
@inproceedings{Haitham2011, address={Taipei, Taiwan},
author={Haitham Bou Ammar and Mathew E. Taylor},
booktitle={Proceedings of the AAMAS 2011 Workshop on Adaptive Learning Agents and Multi-agent Systems (ALA 2011)},
month={May},
title={Common Subspace Transfer for Reinforcement Learning Tasks},
url={http://swarmlab.unimaas.nl/research/publications/},
year=2011, }
-
S. Alers, D. Bloembergen, D. Hennes, and K. Tuyls, Augmented mobile telepresence with assisted control (Demo), in Proc. of 23rd Benelux Conf. on Artificial Intelligence (BNAIC 2011), 2011, pp. 451-452.
@inproceedings{Alers2011a,
author={Sjriek Alers and Daan Bloembergen and Daniel Hennes and Karl Tuyls},
booktitle={Proc. of 23rd Benelux Conf. on Artificial Intelligence (BNAIC 2011)},
pages={451-452},
title={Augmented mobile telepresence with assisted control (Demo)},
url={http://www.flowermountains.nl/pub/Alers2011a.pdf},
year=2011, }
-
M. Ponsen, S. de Jong, and M. Lanctot, Computing Approximate Nash Equilibria and Robust Best-Responses Using Sampling, Journal of Artificial Intelligence Research, vol. 42, pp. 575-605, 2011.
@article{Ponsen2011,
author={Marc Ponsen and Steven de Jong and Marc Lanctot},
journal={Journal of Artificial Intelligence Research},
pages={575--605},
title={Computing Approximate {N}ash Equilibria and Robust Best-Responses Using Sampling},
url={http://www.jair.org/papers/paper3402.html},
volume=42, year=2011, }
-
D. Bloembergen, S. de Jong, and K. Tuyls, Lenient Learning in the Multi-player Stag Hunt, in Proc. of 23rd Benelux Conf. on Artificial Intelligence (BNAIC 2011), 2011, pp. 44-50.
@inproceedings{Bloembergen2011a,
author={Daan Bloembergen and Steven de Jong and Karl Tuyls},
booktitle={Proc. of 23rd Benelux Conf. on Artificial Intelligence (BNAIC 2011)},
pages={44-50},
title={Lenient Learning in the Multi-player Stag Hunt},
url={http://www.flowermountains.nl/pub/Bloembergen2011a.pdf},
year=2011, }
-
M. Kaisers and K. Tuyls, Multi-agent Learning and the Reinforcement Gradient, in Proc. of 9th European Workshop on Multi-agent Systems (EUMAS 2011), 2011.
@inproceedings{Kaisers2011, abstract={The number of proposed reinforcement learning algorithms appears to be ever-growing. This article tackles the diversification by showing a persistent principle in several independent reinforcement learning algorithms that have been applied to multi-agent settings. While their learning structure may look very diverse, algorithms such as Gradient Ascent, Cross learning, variations of Q-learning and Regret minimization all follow the same basic pattern. Variations of Gradient Ascent can be described by the projection dynamics and the other algorithms follow the replicator dynamics. In combination with some modulations of the learning rate and deviations for the sake of exploration, they are primarily different implementations of learning in the direction of the reinforcement gradient.},
author={Kaisers, Michael and Tuyls, Karl},
booktitle={Proc. of 9th European Workshop on Multi-agent Systems (EUMAS 2011)},
keywords={dy-,evolutionary game theory,gradient learning,namical systems,reinforcement learning},
publisher={Maastricht University},
title={{Multi-agent Learning and the Reinforcement Gradient}},
url={http://michaelkaisers.com/publications/2011_EUMAS_MKaisers.pdf},
year=2011, }
-
S. de Jong, D. Hennes, K. Tuyls, and Y. Gal, Meta-strategies in the Colored Trails Game, in Proc. of 10th Intl. Conf. on Autonomous Agents and Multiagent Systems (AAMAS 2011), 2011.
@inproceedings{Jong2011,
author={Steven de Jong and Daniel Hennes and Karl Tuyls and Ya'akov Gal},
booktitle={Proc. of 10th Intl. Conf. on Autonomous Agents and Multiagent Systems (AAMAS 2011)},
title={Meta-strategies in the Colored Trails Game},
url={http://dl.dropbox.com/u/1505034/website/publications/AAMAS2011.pdf},
year=2011, }
-
M. Kaisers and K. Tuyls, FAQ-Learning in Matrix Games: Demonstrating Convergence near Nash Equilibria, and Bifurcation of Attractors in the Battle of Sexes, in Workshop on Interactive Decision Theory and Game Theory (IDTGT 2011), 2011.
@inproceedings{Kaisers2011a, abstract={This article studies Frequency Adjusted Q-learning (FAQ-learning), a variation of Q- learning that simulates simultaneous value function updates. The main contributions are empirical and theoretical support for the convergence of FAQ-learning to attractors near Nash equilibria in two-agent two-action matrix games. The games can be divided into three types: Matching pennies, Prisoners' Dilemma and Battle of Sexes. This article shows that the Matching pennies and Prisoners' Dilemma yield one attractor of the learning dynamics, ...},
author={Kaisers, Michael and Tuyls, Karl},
booktitle={Workshop on Interactive Decision Theory and Game Theory (IDTGT 2011)},
publisher={Assoc. for the Advancement of Artif. Intel. (AAAI)},
title={{FAQ-Learning in Matrix Games: Demonstrating Convergence near Nash Equilibria, and Bifurcation of Attractors in the Battle of Sexes}},
url={http://www.aaai.org/ocs/index.php/WS/AAAIW11/paper/download/3950/4282},
year=2011, }
-
S. Alers, D. Bloembergen, D. Hennes, S. de Jong, M. Kaisers, N. Lemmens, K. Tuyls, and G. Weiss, Bee-inspired foraging in an embodied swarm, in Proceedings of the Tenth International Conference on Autonomous Agents and Multi-Agent Systems (Demo Track), 2011, pp. 1311-1312.
@inproceedings{alers2011aamas,
author={Sjriek Alers and Daan Bloembergen and Daniel Hennes and Steven de Jong and Michael Kaisers and Nyree Lemmens and Karl Tuyls and Gerhard Weiss},
booktitle={Proceedings of the Tenth International Conference on Autonomous Agents and Multi-Agent Systems (Demo Track)},
pages={1311-1312},
title={Bee-inspired foraging in an embodied swarm},
url={http://swarmlab.unimaas.nl/people/publications/},
year=2011, }
-
S. de Jong, D. Hennes, K. Tuyls, and Y. Gal, Meta-strategies in the Colored Trails Game (B-paper), in Proc. of the Benelux Conference on Artificial Intelligence (BNAIC), 2011.
@inproceedings{Jong2011b,
author={Steven de Jong and Daniel Hennes and Karl Tuyls and Ya'akov Gal},
booktitle={Proc. of the Benelux Conference on Artificial Intelligence (BNAIC)},
title={Meta-strategies in the Colored Trails Game (B-paper)},
url={http://dl.dropbox.com/u/1505034/website/publications/AAMAS2011.pdf},
year=2011, }
-
M. Wunder, M. Kaisers, J. R. Yaros, and M. Littman, Using iterated reasoning to predict opponent strategies, in Proc. of 10th Int. Conf. on Autonomous Agents and Multiagent Systems (AAMAS 2011), 2011, pp. 593-600.
@inproceedings{Wunder2011, abstract={The field of multiagent decision making is extending its tools from classical game theory by embracing reinforcement learning, statistical analysis, and opponent modeling. For example, behavioral economists conclude from experimental results that people act according to levels of reasoning that form a ‚Äö?Ñ??cognitive hierarchy‚Äö?Ñ?? of strategies, rather than merely following the hyper-rational Nash equilibrium solution concept. This paper expands this model of the iterative reasoning process by widening the notion of a ...},
author={Wunder, Michael and Kaisers, Michael and Yaros, J.R. and Littman, Michael},
booktitle={Proc. of 10th Int. Conf. on Autonomous Agents and Multiagent Systems (AAMAS 2011)},
editor={Tumer and Yolum and Sonenberg and Stone},
file={:Users/mkaisers/Dropbox/Mendeley/2011 - Using iterated reasoning to predict opponent strategies - Wunder et al.pdf:pdf},
keywords={cognitive models,iterated reasoning,multiagent systems,pomdps,repeated games},
pages={593--600},
publisher={International Foundation for AAMAS},
title={{Using iterated reasoning to predict opponent strategies}},
url={http://paul.rutgers.edu/~mwunder/pub/LG\_PIPOMDP.pdf},
year=2011, }
-
H. B. Ammar, M. E.Taylor, K. Tuyls, and G. Weiss, Common Subspace Transfer for Reinfrocement Learning Tasks (B-paper), in Proc. of the Benelux Conference on Artificial Intelligence (BNAIC), 2011.
@inproceedings{Haitham2011b,
author={Haitham Bou Ammar and Mathew E.Taylor and Karl Tuyls and Gerhard Weiss},
booktitle={Proc. of the Benelux Conference on Artificial Intelligence (BNAIC)},
title={Common Subspace Transfer for Reinfrocement Learning Tasks (B-paper)},
year=2011, }
-
N. Lemmens, S. Alers, and K. Tuyls, Bee-inspired foraging in a real-life autonomous robot collective, in Proceedings of the 23rd Benelux Conference on Artificial Intelligence (BNAIC 2011), 2011, pp. 459-460.
@inproceedings{lemmens2011, abstract={In this demo, we show the emergence of Swarm Intelligence in physical robots. We transferred an optimization algorithm which is based on bee-foraging behavior to a robotic swarm with the advantage that this algorithm, and so the actual robots, do not require input of environmental parameters (e.g., pheromones).},
author={Lemmens, Nyree and Alers, Sjriek and Tuyls, Karl},
booktitle={Proceedings of the 23rd Benelux Conference on Artificial Intelligence (BNAIC 2011)},
journal={Benelux Conference on Artificial Intelligence (BNAIC)},
pages={459--460},
title={Bee-inspired foraging in a real-life autonomous robot collective},
url={http://sjriek.nl/publication/2011-BNAIC-Bee-inspiredForagingInAReal-lifeAutonomousRobotCollective.pdf},
year=2011, }
-
D. Mescheder, K. Tuyls, and M. Kaisers, Opponent Modeling with POMDPs, in Proc. of 23nd Belgium-Netherlands Conf. on Artificial Intelligence (BNAIC 2011), 2011, pp. 152-159.
@inproceedings{Mescheder2011,
author={Mescheder, Daniel and Tuyls, Karl and Kaisers, Michael},
booktitle={Proc. of 23nd Belgium-Netherlands Conf. on Artificial Intelligence (BNAIC 2011)},
pages={152-159},
publisher={KAHO Sint-Lieven, Gent},
title={{Opponent Modeling with POMDPs}},
url={http://michaelkaisers.com/publications/2011_BNAIC_DMescheder.pdf},
year=2011, }
-
K. M. Wurm, D. Hennes, D. Holz, R. B. Rusu, C. Stachniss, K. Konolige, and W. Burgard, Hierarchies of octrees for efficient 3D mapping., in Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), San Francisco, United States, 2011, pp. 4249-4255.
@inproceedings{Wurm2011, address={San Francisco, United States},
author={Wurm, Kai M. and Hennes, Daniel and Holz, Dirk and Rusu, Radu Bogdan and Stachniss, Cyrill and Konolige, Kurt and Burgard, Wolfram},
booktitle={Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
month={September},
pages={4249-4255},
title={Hierarchies of octrees for efficient 3D mapping.},
year=2011, }
-
D. Claes, D. Hennes, and K. Tuyls, Real-world multi-robot collision avoidance with localization uncertainty, in Proceedings of 9th European Workshop on Multi-agent Systems (EUMAS 2011), Maastricht, The Netherlands, 2011.
@inproceedings{Claes2011a, address={Maastricht, The Netherlands},
author={Daniel Claes and Daniel Hennes and Karl Tuyls},
booktitle={Proceedings of 9th European Workshop on Multi-agent Systems (EUMAS 2011)},
month={November},
title={Real-world multi-robot collision avoidance with localization uncertainty},
year=2011, }
-
D. Claes, D. Hennes, and K. Tuyls, Real-world multi-robot collision avoidance with localization uncertainty, in Proceedings of 9th European Workshop on Multi-agent Systems (EUMAS 2011 Demo Track), Maastricht, The Netherlands, 2011.
@inproceedings{Claes2011b, address={Maastricht, The Netherlands},
author={Daniel Claes and Daniel Hennes and Karl Tuyls},
booktitle={Proceedings of 9th European Workshop on Multi-agent Systems (EUMAS 2011 Demo Track)},
month={November},
title={Real-world multi-robot collision avoidance with localization uncertainty},
year=2011, }
-
D. Bloembergen, M. Kaisers, and K. Tuyls, Lenient Frequency Adjusted Q-learning, in Proc. of 22nd Benelux Conf. on Artificial Intelligence (BNAIC 2010), 2010, pp. 19-26.
@inproceedings{Bloembergen2010a,
author={Daan Bloembergen and Michael Kaisers and Karl Tuyls},
booktitle={Proc. of 22nd Benelux Conf. on Artificial Intelligence (BNAIC 2010)},
pages={19--26},
publisher={University of Luxembourg},
title={Lenient Frequency Adjusted {Q}-learning},
url={http://www.flowermountains.nl/pub/Bloembergen2010a.pdf},
year=2010, }
-
S. Van Segbroeck, S. de Jong, A. Nowé, F. Santos, and T. Lenaerts, Learning to coordinate in complex networks, Adaptive Behavior, vol. 18, iss. 5, pp. 416-427, 2010.
@article{vansegbroeck2010,
author={Sven {Van Segbroeck} and Steven {de Jong} and Ann Now\'{e} and Francisco Santos and Tom Lenaerts},
journal={Adaptive Behavior},
number=5, pages={416--427},
title={Learning to coordinate in complex networks},
url={http://dl.dropbox.com/u/1505034/website/publications/Adaptive%20Behavior-2010-Van%20Segbroeck-416-27.pdf},
volume=18, year=2010, }
-
T. Klos, G. J. van Ahee, and K. Tuyls, Evolutionary Dynamics of Regret Minimization, , Balcázar, Bonchi, Gionis, and Sebag, Eds., Springer Berlin / Heidelberg, 2010, vol. 6322, pp. 82-96.
@incollection{klos2010,
author={T. Klos and G.J. {van Ahee} and K. Tuyls},
booktitle={Machine Learning and Knowledge Discovery in Databases},
editor={Balc\'{a}zar and Bonchi and Gionis and Sebag},
pages={82--96},
publisher={Springer Berlin / Heidelberg},
series={Lecture Notes in Computer Science},
title={Evolutionary Dynamics of Regret Minimization},
url={http://www.springerlink.com/index/JQ14117123527219.pdf},
volume=6322, year=2010, }
-
D. Bloembergen, M. Kaisers, and K. Tuyls, A Comparative Study of Multi-agent Reinforcement Learning Dynamics, in Proc. of 22nd Benelux Conf. on Artificial Intelligence (BNAIC 2010), 2010, pp. 11-18.
@inproceedings{Bloembergen2010b,
author={Daan Bloembergen and Michael Kaisers and Karl Tuyls},
booktitle={Proc. of 22nd Benelux Conf. on Artificial Intelligence (BNAIC 2010)},
pages={11--18},
publisher={University of Luxembourg},
title={A Comparative Study of Multi-agent Reinforcement Learning Dynamics},
url={http://www.flowermountains.nl/pub/Bloembergen2010b.pdf},
year=2010, }
-
D. Hennes, M. Kaisers, and K. Tuyls, RESQ-learning in stochastic games, in Adaptive and Learning Agents (ALA 2010) Workshop, 2010.
@inproceedings{Hennes2010,
author={Hennes, Daniel and Kaisers, Michael and Tuyls, Karl},
booktitle={Adaptive and Learning Agents (ALA 2010) Workshop},
keywords={evolutionary,game theory,multi-agent learning,reinforcement learning,replicator dynamics,stochastic games},
title={{RESQ-learning in stochastic games}},
url={http://michaelkaisers.com/publications/2010\_ALA\_DHennes.pdf},
year=2010, }
-
S. de Jong and K. Tuyls, Human-inspired computational fairness, Autonomous Agents and Multi-Agent Systems, pp. 1-24, 2010.
@article{Jong2010,
author={de Jong, Steven and Tuyls, Karl},
journal={Autonomous Agents and Multi-Agent Systems},
note={10.1007/s10458-010-9122-9},
pages={1-24},
publisher={Springer Netherlands},
title={{H}uman-inspired computational fairness},
url={http://dx.doi.org/10.1007/s10458-010-9122-9},
year=2010, }
-
H. Voos and H. B. Ammar, Nonlinear Tracking and Landing Controller for Quadrotor Aerial Robots, in Proc. of IEEE Multi-Conference on Systems and Control, Yokohama, Japan, 2010.
@inproceedings{Haitham2010b, address={Yokohama, Japan},
author={Holger Voos and Haitham Bou Ammar},
booktitle={Proc. of IEEE Multi-Conference on Systems and Control},
month={September},
title={Nonlinear Tracking and Landing Controller for Quadrotor Aerial Robots},
url={http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=5611204},
year=2010, }
-
H. B. Ammar, H. Voos, and W. Ertel, Controller Design for Quadrotor UAV’s using Reinforcement Learning, in Proc. of IEEE Multi-Conference on Systems and Control, Yokohama, Japan, 2010.
@inproceedings{Haitham2010, address={Yokohama, Japan},
author={Haitham Bou Ammar and Holger Voos and Wolfgang Ertel},
booktitle={Proc. of IEEE Multi-Conference on Systems and Control},
month={September},
title={Controller Design for Quadrotor UAV's using Reinforcement Learning},
url={http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=5611206},
year=2010, }
-
M. Wunder, M. Kaisers, M. Littman, and J. R. Yaros, A Cognitive Hierarchy Model Applied to the Lemonade Game, in Workshop on Interactive Decision Theory and Game Theory (IDTGT 2010), 2010.
@inproceedings{Wunder2010, abstract={One of the challenges of multiagent decision making is that the behavior needed to maximize utility can depend on what other agents choose to do: sometimes there is no “right” answer in the absence of knowledge of how opponents will act. The Nash equilibrium is a sensible choice of behavior because it represents a mutual best response. But, even when there is a unique equilibrium, other players are under no obligation to take part in it. This observation has been forcefully illustrated in the behavioral economics community ...},
author={Wunder, Michael and Kaisers, Michael and Littman, Michael and Yaros, John Robert},
booktitle={Workshop on Interactive Decision Theory and Game Theory (IDTGT 2010)},
publisher={Assoc. for the Advancement of Artif. Intel. (AAAI)},
title={{A Cognitive Hierarchy Model Applied to the Lemonade Game}},
url={http://www.aaai.org/ocs/index.php/WS/AAAIW10/paper/viewPDFInterstitial/1997/2466},
year=2010, }
-
N. Lemmens and K. Tuyls, Stigmergic landmark routing: a routing algorithm for wireless mobile ad-hoc networks, in Proceedings of the 12th annual conference on Genetic and evolutionary computation, 2010, pp. 47-54.
@inproceedings{Lemmens10a,
author={Lemmens, N. and Tuyls, K.},
booktitle={Proceedings of the 12th annual conference on Genetic and evolutionary computation},
organization={ACM},
pages={47--54},
title={{Stigmergic landmark routing: a routing algorithm for wireless mobile ad-hoc networks}},
url={http://portal.acm.org/citation.cfm?id=1830491},
year=2010, }
-
M. Kaisers and K. Tuyls, Replicator Dynamics for Multi-agent Learning – An Orthogonal Approach, , Taylor, M. E. and Tuyls, K., Eds., Springer Berlin/Heidelberg, 2010, pp. 49-59.
@incollection{Kaisers2010Orthogonal, abstract={Today’s society is largely connected and many real life appli- cations lend themselves to be modeled as multi-agent systems. Although such systems as well as their models are desirable, e.g., for reasons of stability or parallelism, they are highly complex and therefore difficult to understand or predict. Multi-agent learning has been acknowledged to be indispensable to control or find solutions for such systems. Recently, evolutionary game theory has been linked to multi-agent reinforcement learning. However, gaining insight into the dynamics of games, especially if time dependent, remains a challenging problem. This article introduces a new perspective on the reinforcement learning process described by the replicator dynamics, providing a tool to design time dependent parame- ters of the game or the learning process. This perspective is orthogonal to the common view of policy trajectories driven by the replicator dy- namics. Rather than letting the time dimension collapse, the set of initial policies is considered to be a particle cloud that approximates a distri- bution and we look at the evolution of this distribution over time. First, the methodology is described, then it is applied to an example game and viable extensions are discussed.},
author={Kaisers, Michael and Tuyls, Karl},
booktitle={Adaptive and Learning Agents, LNAI},
editor={Taylor, Matthew E. and Tuyls, Karl},
keywords={evolutionary game theory,reinforcement learning},
pages={49--59},
publisher={Springer Berlin/Heidelberg},
title={{Replicator Dynamics for Multi-agent Learning - An Orthogonal Approach}},
url={http://www.springerlink.com/index/77G519902M773965.pdf},
year=2010, }
-
M. Kaisers and K. Tuyls, Frequency Adjusted Multi-agent Q-learning, in Proc. of 9th Intl. Conf. on Autonomous Agents and Multiagent Systems (AAMAS 2010), 2010, pp. 309-315.
@inproceedings{Kaisers2010FAQ, abstract={Multi-agent learning is a crucial method to control or find solutions for systems, in which more than one entity needs to be adaptive. In today’s interconnected world, such sys- tems are ubiquitous in many domains, including auctions in economics, swarm robotics in computer science, and politics in social sciences. Multi-agent learning is inherently more complex than single-agent learning and has a relatively thin theoretical framework supporting it. Recently, multi-agent learning dynamics have been linked to evolutionary game theory, allowing the interpretation of learning as an evolu- tion of competing policies in the mind of the learning agents. The dynamical system from evolutionary game theory that has been linked to Q-learning predicts the expected behav- ior of the learning agents. Closer analysis however allows for two interesting observations: the predicted behavior is not always the same as the actual behavior, and in case of deviation, the predicted behavior is more desirable. This discrepancy is elucidated in this article, and based on these new insights Frequency Adjusted Q- (FAQ-) learning is pro- posed. This variation of Q-learning perfectly adheres to the predictions of the evolutionary model for an arbitrarily large part of the policy space. In addition to the theoretical dis- cussion, experiments in the three classes of two-agent two- action games illustrate the superiority of FAQ-learning.},
author={Kaisers, Michael and Tuyls, Karl},
booktitle={Proc. of 9th Intl. Conf. on Autonomous Agents and Multiagent Systems (AAMAS 2010)},
editor={van der Hoek and Kamina and Lesp\'{e}rance and Luck and Sen},
keywords={Evolutionary game theory,Multi-agent learning,Q-learning,Replicator dynamics},
pages={309--315},
title={{Frequency Adjusted Multi-agent Q-learning}},
url={http://dl.acm.org/citation.cfm?id=1838250},
year=2010, }
-
J. Hu and S. Alers, AdMoVeo: Created For Teaching Creative Programming, in Workshop Proceedings of the 18th International Conference on Computers in Education (ICCE 2010), Putrajaya, Malaysia, 2010, pp. 361-365.
@inproceedings{citeulike:9108783, address={Putrajaya, Malaysia},
author={Hu, Jun and Alers, Sjriek},
booktitle={Workshop Proceedings of the 18th International Conference on Computers in Education (ICCE 2010)},
citeulike-article-id=9108783, citeulike-linkout-0={http://www.drhu.eu/publications/2010-ICCE-AdMoVeoCreatedForTeachingCreativeProgramming/index.html},
editor={Hirashima, Tsukasa and Mohd Ayub, Ahmad F. and Kwok, Lam-For and Wong, Su L. and Kong, Siu C. and Yu, Fu-Yun},
pages={361--365},
pdf={http://www.drhu.eu/publications/2010-ICCE-AdMoVeoCreatedForTeachingCreativeProgramming.pdf},
posted-at={2011-04-06 18:50:55},
priority=2, publisher={Universiti Putra Malaysia},
title={{AdMoVeo}: Created For Teaching Creative Programming},
url={http://www.drhu.eu/publications/2010-ICCE-AdMoVeoCreatedForTeachingCreativeProgramming/index.html},
year=2010, }
-
M. Ponsen, M. Lanctot, and S. de Jong, MCRNR: Fast Computing of Restricted Nash Responses by Means of Sampling, in Proceedings of Interactive Decision Theory and Game Theory Workshop at the Twenty-Fourth Conference on Artificial Intelligence (AAAI-10), 2010.
@inproceedings{Ponsen2010,
author={Marc Ponsen and Marc Lanctot and Steven de Jong},
booktitle={Proceedings of {Interactive Decision Theory and Game Theory} Workshop at the Twenty-Fourth Conference on Artificial Intelligence (AAAI-10)},
publisher={AAAI press},
title={{MCRNR}: {F}ast {C}omputing of {R}estricted {N}ash {R}esponses by {M}eans of {S}ampling},
year=2010, }
-
S. de Jong and K. Tuyls, Learning to cooperate in a continuous Tragedy of the Commons, in Proceedings of the 8th International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS 2009), 2009, pp. 1185-1186.
@inproceedings{Jong2009,
author={Steven de Jong and Karl Tuyls},
booktitle={Proceedings of the 8th International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS 2009)},
pages={1185--1186},
title={{L}earning to cooperate in a continuous {T}ragedy of the {C}ommons},
url={http://dl.dropbox.com/u/1505034/website/publications/aamas2009.pdf},
year=2009, }
-
J. Hu and S. Alers, AdMoVeo: An Educational Robotic Platform For Learning Behavior Programming, in DeSForM 2009: Design and Semantics of Form and Movement, 2009, pp. 218-219.
@inproceedings{HuJun2009,
author={{Hu, Jun} and {Alers, Sjriek}},
booktitle={{DeSForM 2009: Design and Semantics of Form and Movement}},
pages={218--219},
title={AdMoVeo: An Educational Robotic Platform For Learning Behavior Programming},
url={http://www.drhu.eu/publications/2009-DeSForM-AdMoVeo-AnEducationalRoboticPlatformForLearningBehaviorProgramming/index.html},
year=2009, }
-
M. Ponsen, K. Tuyls, M. Kaisers, and J. Ramon, An evolutionary game-theoretic analysis of poker strategies, in Entertainment Computing, 2009, pp. 39-45.
@inproceedings{Ponsen2009a,
author={Marc Ponsen and Karl Tuyls and Michael Kaisers and Jan Ramon},
booktitle={Entertainment Computing},
pages={39-45},
title={{A}n evolutionary game-theoretic analysis of poker strategies},
url={http://www.personeel.unimaas.nl/m-ponsen/pubs/Ponsen-Tuyls-Kaisers-Ramon_EGT.pdf},
volume=1, year=2009, }
-
S. Alers and J. Hu, AdMoVeo: A Robotic Platform for Teaching Creative Programming to Designers, Learning by Playing. Game-based Education System Design and Development, pp. 410-421, 2009.
-
Alers, Sjriek and Barakova, Emilia I., Multi-agent platform for development of educational games for children with autism, 2009.
-
S. de Jong, False information and the emergence of conflict, in Proceedings of BNAIC, 2009.
@inproceedings{Jong2009b,
author={Steven de Jong},
booktitle={Proceedings of BNAIC},
title={{F}alse information and the emergence of conflict},
url={http://dl.dropbox.com/u/1505034/website/publications/dejong2009bnaic.pdf},
year=2009, }
-
M. Kaisers, Replicator Dynamics for Multi-agent Learning – An Orthogonal Approach, in Proc. of the 21st Benelux Conference on Artificial Intelligence (BNAIC 2009), Eindhoven, 2009, pp. 113-120.
@inproceedings{Kaisers2009a, abstract={Today’s society is largely connected and many real life applications lend themselves to be modeled as multi-agent systems. Although such systems as well as their models are desirable, e.g. for reasons of sta- bility or parallelism, they are highly complex and therefore difficult to understand or predict. Multi-agent learning has been acknowledged to be indispensable to control or find solutions for such systems. Re- cently, evolutionary game theory has been linked to multi-agent reinforcement learning. However, gaining insight into the dynamics of games, especially if time dependent, remains a challenging problem. This article introduces a new perspective on the reinforcement learning process described by the replicator dy- namics, providing a tool to design time dependent parameters of the game or the learning process. This perspective is orthogonal to the common view of policy trajectories driven by the replicator dynamics. Rather than letting the time dimension collapse, the set of initial policies is considered to be a particle cloud that approximates a distribution and we look at the evolution of this distribution over time. First, the methodology is described, then it is applied to an example game and viable extensions are discussed.},
address={Eindhoven},
author={Kaisers, Michael},
booktitle={Proc. of the 21st Benelux Conference on Artificial Intelligence (BNAIC 2009)},
editor={Calders, Toon and Tuyls, Karl and Pechenizkiy, Mykola},
keywords={evolutionary game theory,reinforcement learning},
pages={113--120},
publisher={Eindhoven University of Technology},
title={{Replicator Dynamics for Multi-agent Learning - An Orthogonal Approach}},
year=2009, }
-
N. Lemmens and K. Tuyls, Stigmergic Landmark Foraging, in Proceedings of the eigth international conference on Autonomous Agents and Multi Agent Systems (AAMAS), 2009.
@inproceedings{Lemmens09a,
author={Nyree Lemmens and Karl Tuyls},
booktitle={Proceedings of the eigth international conference on Autonomous Agents and Multi Agent Systems (AAMAS)},
title={Stigmergic Landmark Foraging},
url={http://portal.acm.org/citation.cfm?id=1558081},
year=2009, }
-
M. Kaisers, K. Tuyls, and S. Parsons, An Evolutionary Model of Multi-agent Learning with a Varying Exploration Rate (Extended Abstract), in Proc. of 8th Int. Conf. on Autonomous Agents and Multiagent Systems (AAMAS 2009), 2009, pp. 1255-1256.
@inproceedings{Kaisers2009, abstract={Multi-agent learning is a challenging problem and has recently attracted increased attention by the research community [4, 5]. It promises control over complex multi-agent systems such that agents enact a global desired behavior while operating on local knowledge.},
author={Kaisers, Michael and Tuyls, Karl and Parsons, Simon},
booktitle={Proc. of 8th Int. Conf. on Autonomous Agents and Multiagent Systems (AAMAS 2009)},
keywords={auctions,dynamics,evolutionary game theory,multi-agent learning,q-learning,replicator},
pages={1255--1256},
publisher={International Foundation for AAMAS},
title={{An Evolutionary Model of Multi-agent Learning with a Varying Exploration Rate (Extended Abstract)}},
year=2009, }
-
S. de Jong, Fairness in Multi-Agent Systems, PhD Thesis , 2009.
@phdthesis{jong2009a,
author={Steven de Jong},
school={Maastricht University},
title={{F}airness in {M}ulti-{A}gent {S}ystems},
url={http://dl.dropbox.com/u/1505034/website/optima/thesis(17x24).pdf},
year=2009, }
-
D. Hennes and K. Tuyls, State-Coupled Replicator Dynamics, in AAMAS, 2009.
@inproceedings{hennes2009a,
author={Daniel Hennes and Karl Tuyls},
booktitle={AAMAS},
title={{S}tate-{C}oupled {R}eplicator {D}ynamics},
url={http://portal.acm.org/citation.cfm?id=1558120},
year=2009, }
-
D. Hennes, K. P. Tuyls, M. A. Neerincx, and G. W. M. Rauterberg, Micro-scale social network analysis for ultra-long space flights, in IJCAI Workshop on Artificial Intelligence in Space, 2009.
@inproceedings{Hennes2009,
author={D. Hennes and K. P. Tuyls and M. A. Neerincx and G. W. M. Rauterberg},
booktitle={IJCAI Workshop on Artificial Intelligence in Space},
title={{M}icro-scale social network analysis for ultra-long space flights},
url={http://www.idemployee.id.tue.nl/g.w.m.rauterberg/publications/ijcai2009paper.pdf},
year=2009, }
-
S. de Jong, K. Tuyls, and K. Verbeeck, Artificial Agents Learning Human Fairness, in Proceedings of the international joint conference on Autonomous Agents and Multi-Agent Systems (AAMAS’08), 2008, pp. 863-870.
@inproceedings{Jong2008c,
author={Steven de Jong and Karl Tuyls and Katja Verbeeck},
booktitle={Proceedings of the international joint conference on Autonomous Agents and Multi-Agent Systems (AAMAS'08)},
pages={863--870},
title={{A}rtificial {A}gents {L}earning {H}uman {F}airness},
url={http://dl.dropbox.com/u/1505034/website/publications/AgentsLearningFairness.pdf},
year=2008, }
-
S. de Jong and K. Tuyls, Learning to cooperate in public-goods interactions. 2008.
@inproceedings{Jong2008d,
author={Steven de Jong and Karl Tuyls},
note={Presented at the EUMAS'08 Workshop, Bath, UK, December 18-19},
title={{L}earning to cooperate in public-goods interactions},
url={http://dl.dropbox.com/u/1505034/website/publications/pgg.pdf},
year=2008, }
-
D. Hennes, K. Tuyls, and M. Rauterberg, Formalizing Multi-State Learning Dynamics, in IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology, 2008, pp. 266-272.
@inproceedings{Hennes2008,
author={Daniel Hennes and Karl Tuyls and Matthias Rauterberg},
booktitle={IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology},
month={Dec},
pages={266--272},
title={{F}ormalizing {M}ulti-{S}tate {L}earning {D}ynamics},
url={http://www.computer.org/portal/web/csdl/doi/10.1109/WIIAT.2008.33},
volume=2, year=2008, }
-
D. Hennes, M. Kaisers, and K. Tuyls, A Multiagent Approach to Hyper-Redundant Manipulators, in Proceedings of the AAMAS 2008 Workshop on Adaptive Learning Agents and Multi-Agent Systems (ALAMAS+ALAg 2008), Estoril, Portugal, 2008.
@inproceedings{Hennes2008a, address={Estoril, Portugal},
author={Hennes, Daniel and Kaisers, Michael and Tuyls, Karl},
booktitle={Proceedings of the AAMAS 2008 Workshop on Adaptive Learning Agents and Multi-Agent Systems (ALAMAS+ALAg 2008)},
month={May},
title={A Multiagent Approach to Hyper-Redundant Manipulators},
year=2008, }
-
L. Panait, K. Tuyls, and S. Luke, Theoretical Advantages of Lenient Learners: An Evolutionary Game Theoretic Perspective, Journal of Machine Learning Research (JMLR), vol. 9, pp. 423-457, 2008.
@article{Panait2008a,
author={L. Panait and K. Tuyls and S. Luke},
journal={Journal of Machine Learning Research (JMLR)},
pages={423-457},
title={{T}heoretical {A}dvantages of {L}enient {L}earners: {A}n {E}volutionary {G}ame {T}heoretic {P}erspective},
volume=9, year=2008, }
-
P. Vrancx, K. Tuyls, R. Westra, and A. Nowe, Switching Dynamics of Multi-Agent Learning., in Proceedings of the seventh joint conference on autonomous agents and multi-agent systems, Estoril, Portugal, 2008, pp. 307-314.
@inproceedings{Vrancx2008c,
author={Vrancx, P. and Tuyls, K. and Westra, R. and Nowe, A.},
booktitle={Proceedings of the seventh joint conference on autonomous agents and multi-agent systems, Estoril, Portugal},
pages={307-314},
title={{S}witching {D}ynamics of {M}ulti-{A}gent {L}earning.},
year=2008, }
-
N. Lemmens, S. de Jong, K. Tuyls, and A. Now̩, Bee behaviour in multi-agent systems: A bee foraging algorithm, In Adaptive Agents and Multi-Agent Systems III РLecture Notes in Artificial Intelligence, vol. 4865, 2008.
@article{Lemmens2008,
author={Nyree Lemmens and Steven de Jong and Karl Tuyls and Ann Now\'{e}},
journal={In Adaptive Agents and Multi-Agent Systems III - Lecture Notes in Artificial Intelligence},
title={{B}ee behaviour in multi-agent systems: {A} bee foraging algorithm},
volume=4865, year=2008, }
-
S. de Jong, K. Tuyls, K. Verbeeck, and N. Roos, Priority awareness: towards a computational model of human fairness for multi-agent systems, Adaptive Agents and Multi-Agent Systems III – Lecture Notes in Artificial Intelligence, vol. 4865, 2008.
@article{Jong2008a,
author={Steven de Jong and Karl Tuyls and Katja Verbeeck and Nico Roos},
journal={Adaptive Agents and Multi-Agent Systems III - Lecture Notes in Artificial Intelligence},
title={{P}riority awareness: towards a computational model of human fairness for multi-agent systems},
url={http://dl.dropbox.com/u/1505034/website/publications/DeJong-PriorityAwareness.pdf/},
volume=4865, year=2008, }
-
S. de Jong, K. Tuyls, and K. Verbeeck, Fairness in multi-agent systems, Knowledge Engineering Review, iss. 23, pp. 153-180, 2008.
@article{Jong2008b,
author={Steven de Jong and Karl Tuyls and Katja Verbeeck},
journal={Knowledge Engineering Review},
number=23, pages={153--180},
title={{F}airness in multi-agent systems},
url={http://dl.dropbox.com/u/1505034/website/publications/dejong-ker-2008.pdf},
year=2008, }
-
M. Kaisers, Games and Learning in Auctions, Master’s Dissertation , 2008.
@mastersthesis{Kaisers2008, abstract={Auctions are pervasive in today’s society and provide a variety of markets, ranging from government-to-business auctions for licenses to consumer-to- consumer online auctions. The success of trading strategies in auctions is highly dependent on the present competitors, hence traders are forced to adapt to the competition to maintain a high level of performance. This adaptation may be modeled by reinforcement learning algorithms, which have a proven relation to evolutionary game theory. This thesis facilitates a strategic choice between a set of predefined trad- ing strategies. It is based on previous work, which suggests to capture the payoff of trading strategies in a heuristic payoff table. A new methodology to approximate heuristic payoff tables by normal form games is introduced, and it is evaluated by a case study of a 6-agent clearing house auction. Learning models of exploration and exploitation, that link to selection and mutation in an evolutionary perspective, are subsequently applied to compare three common automated trading strategies. The information loss in the normal form approximation is shown to be reasonably small, such that the concise normal form representation can be used to derive strategic decisions in auctions. Furthermore, the learning model shows that learners with exploration may converge to different strate- gies than learners of pure exploitation. The devised methodology establishes a bridge between empirical data in heuristic payoff tables and the means from classical game theory. It might therefore become the basis for a more general framework to analyze strategic interactions in complex multi-agent systems.},
author={Kaisers, Michael},
keywords={Auctions,Evolutionary game theory,Multi-agent learning},
school={Maastricht University},
title={{Games and Learning in Auctions}},
year=2008, }
-
N. Lemmens and K. Tuyls, Stigmergic Landmarks Lead The Way, in The 20th Belgian-Dutch Conference on Artificial Intelligence (BNAIC), 2008, pp. 129-136.
@inproceedings{Lemmens08b,
author={Nyree Lemmens and Karl Tuyls},
booktitle={The 20th Belgian-Dutch Conference on Artificial Intelligence (BNAIC)},
file={:P\:\\PhD\\Symposium, Conference, and Journal Papers\\BNAIC2008.pdf:PDF;Lemmens08b.pdf:Personal Publications\\Lemmens08b.pdf:PDF},
pages={129--136},
title={Stigmergic Landmarks Lead The Way},
url={http://nyreelemmens.weebly.com/uploads/2/4/4/0/2440722/bnaic2008.pdf},
year=2008, }
-
M. Kaisers, K. Tuyls, and F. Thuijsman, Discovering the game in auctions, in Proc. of 20th Belgian-Netherlands Conference on Artificial Intelligence (BNAIC 2008), 2008, pp. 113-120.
@inproceedings{Kaisers2008a, abstract={Auctions are pervasive in today's society. They provide a variety of markets, ranging from consumer-toconsumer online auctions to government-to-business auctions for telecommunications spectrum licenses. Starting from a set of trading strategies, this article enables a strategic choice by introducing the use of linear programming as a methodology to approximate heuristic payoff tables by normal form games. This method is evaluated on data from auction simulation by applying an evolutionary game theory analysis. The ...},
author={Kaisers, Michael and Tuyls, Karl and Thuijsman, Frank},
booktitle={Proc. of 20th Belgian-Netherlands Conference on Artificial Intelligence (BNAIC 2008)},
keywords={auction theory,evolutionary game theory,multi-agent games},
pages={113--120},
publisher={University of Twente},
title={{Discovering the game in auctions}},
url={http://www.sci.brooklyn.cuny.edu/~parsons/projects/mech-design/publications/bnaic08.pdf},
year=2008, }
-
M. E. Taylor, N. K. Jong, and P. Stone, Transferring Instances for Model-Based Reinforcement Learning, in ECML, 2008.
@inproceedings{o,
author={Matthew E. Taylor and Nicholas K. Jong and Peter Stone},
booktitle={{ECML}},
title={Transferring Instances for Model-Based Reinforcement Learning},
year=2008, }
-
S. de Jong, S. Uyttendaele, and K. Tuyls, Learning to Reach Agreement in a Continuous Ultimatum Game, Journal of Artificial Intelligence Research, vol. 33, pp. 551-574, 2008.
@article{Jong2008,
author={Steven de Jong and Simon Uyttendaele and Karl Tuyls},
journal={Journal of Artificial Intelligence Research},
pages={551--574},
title={{L}earning to {R}each {A}greement in a {C}ontinuous {U}ltimatum {G}ame},
url={http://dl.dropbox.com/u/1505034/website/publications/dejong2008a.pdf},
volume=33, year=2008, }
-
M. Kaisers, K. Tuyls, F. Thuijsman, and S. Parsons, Auction Analysis by Normal Form Game Approximation, in Proc. of Int. Conf. on Web Intelligence and Intelligent Agent Technology (WI-IAT 2008), 2008, pp. 447-450.
@inproceedings{Kaisers2008b, abstract={Auctions are pervasive in todaypsilas society and provide a variety of real markets. This article facilitates a strategic choice between a set of available trading strategies by introducing a methodology to approximate heuristic payoff tables by normal form games. An example from the auction domain is transformed by this means and an evolutionary game theory analysis is applied subsequently. The information loss in the normal form approximation is shown to be reasonably small such that the concise normal form ...},
author={Kaisers, Michael and Tuyls, Karl and Thuijsman, Frank and Parsons, Simon},
booktitle={Proc. of Int. Conf. on Web Intelligence and Intelligent Agent Technology (WI-IAT 2008)},
doi={10.1109/WIIAT.2008.261},
isbn={978-0-7695-3496-1},
month=dec, pages={447--450},
publisher={IEEE/WIC/ACM},
title={{Auction Analysis by Normal Form Game Approximation}},
url={http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=4740664},
year=2008, }
-
N. Lemmens, S. de Jong, K. Tuyls, and A. Nowé, Bee System with inhibition Pheromones, in The 19th Belgian-Dutch Conference on Artificial Intelligence (BNAIC), 2007, pp. 373-375.
@inproceedings{Lemmens07d,
author={Nyree Lemmens and Steven de Jong and Karl Tuyls and Ann Now\'{e}},
booktitle={The 19th Belgian-Dutch Conference on Artificial Intelligence (BNAIC)},
file={Lemmens07d.pdf:Personal Publications\\Lemmens07d.pdf:PDF;Lemmens07d.pdf:Personal Publications\\Lemmens07d.pdf:PDF},
note={B-Paper (Originally published at ECCS 2007)},
pages={373--375},
title={Bee System with inhibition Pheromones},
url={http://como.vub.ac.be/~nlemmens/Publications/NiSIS2007.pdf},
year=2007, }
-
N. Lemmens, S. de Jong, K. Tuyls, and A. Nowé, Bee System with inhibition Pheromones, in The 19th Belgian-Dutch Conference on Artificial Intelligence (BNAIC), 2007, pp. 373-375.
@inproceedings{lemmens07d2,
author={Nyree Lemmens and Steven de Jong and Karl Tuyls and Ann Now\'{e}},
booktitle={The 19th Belgian-Dutch Conference on Artificial Intelligence (BNAIC)},
file={Lemmens07d.pdf:Personal Publications\\Lemmens07d.pdf:PDF;Lemmens07d.pdf:Personal Publications\\Lemmens07d.pdf:PDF},
note={B-Paper (Originally published at ECCS 2007)},
pages={373--375},
title={Bee System with inhibition Pheromones},
url={http://como.vub.ac.be/~nlemmens/Publications/NiSIS2007.pdf},
year=2007, }
-
Proceedings of the 7th ALAMAS Symposium, 2007.
@proceedings{alamas2007, editor={Karl Tuyls and Steven de Jong and Marc Ponsen and Katja Verbeeck},
number={ISSN 0922-8721, number 07-04},
series={MICC Technical Report Series},
title={{P}roceedings of the 7th {ALAMAS} {S}ymposium},
year=2007, }
-
N. Lemmens, S. de Jong, K. Tuyls, and A. Nowé, Bee System with inhibition Pheromones, in Proceedings of NiSIS 2007, 2007.
@inproceedings{Lemmens07e,
author={Nyree Lemmens and Steven de Jong and Karl Tuyls and Ann Now\'{e}},
booktitle={Proceedings of NiSIS 2007},
file={Lemmens07e.pdf:Personal Publications\\Lemmens07e.pdf:PDF;Lemmens07e.pdf:Personal Publications\\Lemmens07e.pdf:PDF},
note={B-Paper (Originally published at ECCS 2007)},
title={Bee System with inhibition Pheromones},
url={http://www.nisis.risk-technologies.com/(S(oqh5ai45mkcti1epbbonunqa))/events/symp2007/papers/AB22_P_Lemmens.pdf},
year=2007, }
-
J. H. van den Herik, D. Hennes, M. Kaisers, K. Tuyls, and K. Verbeeck, Multi-agent learning dynamics: A survey, Cooperative Information Agents XI, vol. 4676, pp. 36-56, 2007.
@article{VandenHerik2007, abstract={In this paper we compare state-of-the-art multi-agent reinforcement learning algorithms in a wide variety of games. We consider two types of algorithms: value iteration and policy iteration. Four characteristics are studied: initial conditions, parameter settings, convergence speed, and local versus global convergence. Global convergence is still difficult to achieve in practice, despite existing theoretical guarantees. Multiple visualizations are included to provide a comprehensive insight into the learning dynamics.},
author={van den Herik, Jaap H. and Hennes, Daniel and Kaisers, Michael and Tuyls, Karl and Verbeeck, Katja},
journal={Cooperative Information Agents XI},
pages={36--56},
publisher={Springer},
title={{Multi-agent learning dynamics: A survey}},
url={http://www.springerlink.com/index/dh25513561546332.pdf},
volume=4676, year=2007, }
-
N. Lemmens, S. de Jong, K. Tuyls, and A. Nowé, A Bee Algorithm for Multi-Agent Systems: Recruitment and Navigation Combined, in Proceedings of ALAg, an AAMAS workshop, 2007, pp. 66-70.
@inproceedings{Lemmens07b,
author={Nyree Lemmens and Steven de Jong and Karl Tuyls and Ann Now\'{e}},
booktitle={Proceedings of ALAg, an AAMAS workshop},
file={Lemmens07b.pdf:Personal Publications\\Lemmens07b.pdf:PDF;Lemmens07b.pdf:Personal Publications\\Lemmens07b.pdf:PDF},
pages={66--70},
title={A Bee Algorithm for Multi-Agent Systems: Recruitment and Navigation Combined},
url={http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.129.7808&rep=rep1&type=pdf},
year=2007, }
-
N. Lemmens, S. de Jong, K. Tuyls, and A. Nowé, Bee System with inhibition Pheromones, in European Conference on Complex Systems (ECCS), 2007.
@inproceedings{Lemmens07c,
author={Nyree Lemmens and Steven de Jong and Karl Tuyls and Ann Now\'{e}},
booktitle={European Conference on Complex Systems (ECCS)},
file={Lemmens07c.pdf:Personal Publications\\Lemmens07c.pdf:PDF;Lemmens07c.pdf:Personal Publications\\Lemmens07c.pdf:PDF},
title={Bee System with inhibition Pheromones},
url={http://cssociety.org/tiki-index.php?page=ECCS07-299+&bl},
year=2007, }
-
S. de Jong, K. Tuyls, K. Verbeeck, and N. Roos, Considerations for fairness in multi-agent systems, in Proceedings of the 7th ALAMAS Symposium, 2007, p. pp.104-110.
@inproceedings{Jong2007,
author={Steven de Jong and Karl Tuyls and Katja Verbeeck and Nico Roos},
booktitle={Proceedings of the 7th ALAMAS Symposium},
pages={pp.104--110},
title={{C}onsiderations for fairness in multi-agent systems},
url={http://dl.dropbox.com/u/1505034/website/publications/alamas07_dejong.pdf},
year=2007, }
-
M. Kaisers, Reinforcement Learning in Multi-agent Games – A value iteration perspective, 2007.
@techreport{Kaisers2007, abstract={This article investigates the performance of independent reinforcement learners in multi- agent games. Convergence to Nash equilibria and parameter settings for desired learning be- havior are discussed for Q-learning, Frequency Maximum Q value (FMQ) learning and lenient Q-learning. FMQ and lenient Q-learning are shown to outperform regular Q-learning significantly in the context of coordination games with mis- coordination penalties. Furthermore, Q- learning with an $\epsilon$-greedy and FMQ learning with a Boltzmann action selection are shown to scale well to games with one thousand agents.},
author={Kaisers, Michael},
keywords={FMQ-learning,Q-learning,iterated games,learning,lenient Q- learning,lenient q-,reinforcement iterated games,reinforcement learning},
school={Maastricht University},
title={{Reinforcement Learning in Multi-agent Games - A value iteration perspective}},
year=2007, }
-
K. Tuyls and S. Parsons, What evolutionary game theory tells us about multiagent learning, AI, vol. 171, 2007.
@article{Tuyls2007, abstract={This paper discusses If multi-agent learning is the answer, what is the question? [20] from the perspective of evolutionary game theory. We briefly discuss the concepts of evolutionary game theory, and examine the main conclusions from [20] with respect to some of our previous work. Overall we find much to agree with, concluding, however, that the central concerns of multiagent learning are rather narrow compared with the broad variety of work identified in [20].},
author={Karl Tuyls and Simon Parsons},
bib2html_pubtype={Journal},
bib2html_rescat={Multi-Agent Learning},
journal={AI},
thepages={406-416},
title={{W}hat evolutionary game theory tells us about multiagent learning},
volume=171, year=2007, }
-
N. Lemmens, S. de Jong, K. Tuyls, and A. Nowe, Bee behaviour in multi-agent systems: a bee foraging algorithm, in Proceedings of the 7th ALAMAS Symposium, 2007, p. pp.126-138.
@inproceedings{Lemmens2007a,
author={Nyree Lemmens and Steven de Jong and Karl Tuyls and Ann Nowe},
booktitle={Proceedings of the 7th ALAMAS Symposium},
pages={pp.126--138},
title={{B}ee behaviour in multi-agent systems: a bee foraging algorithm},
url={http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.135.7453&rep=rep1&type=pdf},
year=2007, }
-
S. de Jong, K. Tuyls, N. Roos, and K. Verbeeck, A descriptive model of priority-based fairness, MICC/IKAT, Maastricht University, 07-01, 2007.
@techreport{Jong2007a,
author={Steven de Jong and Karl Tuyls and Nico Roos and Katja Verbeeck},
institution={MICC/IKAT, Maastricht University},
number={07-01},
title={{A} descriptive model of priority-based fairness},
url={http://dl.dropbox.com/u/1505034/website/publications/TR-MICC-07-01.pdf},
year=2007, }
-
K. Verbeeck, A. Nowé, J. Parent, and K. Tuyls, Exploring selfish reinforcement learning in repeated games with stochastic rewards, Autonomous Agents and Multi-Agent Systems, vol. 4, iss. 13, pp. 239-269, 2006.
@article{Verbeeck2006,
author={Katja Verbeeck and Ann Now\'e and Johan Parent and Karl Tuyls},
journal={Autonomous Agents and Multi-Agent Systems},
month={November},
number=13, pages={239--269},
title={{E}xploring selfish reinforcement learning in repeated games with stochastic rewards },
volume=4, year=2006, }
-
K. Tuyls, P. J. ‘t. Hoen, and B. Vanschoenwinkel, An Evolutionary Dynamical Analysis of Multi-Agent Learning in Iterated Games, J. AAMAS, vol. 12, 2006.
@article{Tuyls2006,
author={Karl Tuyls and Pieter Jan 't Hoen and Bram Vanschoenwinkel},
journal={J. AAMAS},
themonth={January},
thenumber=1, thepages={115--153},
title={{A}n {E}volutionary {D}ynamical {A}nalysis of {M}ulti-{A}gent {L}earning in {I}terated {G}ames},
volume=12, year=2006, }
-
T. Croonenborghs, K. Tuyls, J. Ramon, and M. Bruynooghe, Multi-Agent Relational Reinforcement Learning. Explorations in Multi-State Coordination Tasks, , Tuyls, K., ‘t Hoen, P. J., Verbeeck, K., and Sen, S., Eds., Berlin: Springer Verlag, 2006, vol. 3898, pp. 198-212.
@incollection{Croonenborghs2006, abstract={In this paper we report on using a relational state space in multi-agent reinforcement learning. There is growing evidence in the Reinforcement Learning research community that a relational representation of the state space has many benefits over a propositional one. Complex tasks as planning or information retrieval on the web can be represented more naturally in relational form. Yet, this relational structure has not been exploited for multi-agent reinforcement learning tasks and has only been studied in a single agent context so far. In this paper we explore the powerful possibilities of using Relational Reinforcement Learning (RRL) in complex multi-agent coordination tasks. More precisely, we consider an abstract multi-state coordination problem, which can be considered as a variation and extension of repeated stateless Dispersion Games. Our approach shows that RRL allows to represent a complex state space in a multi-agent environment more compactly and allows for fast convergence of learning agents. Moreover, with this technique, agents are able to make complex interactive models (in the sense of learning from an expert), to predict what other agents will do and generalize over this model. This enables to solve complex multi-agent planning tasks, in which agents need to be adaptive and learn, with more powerful tools.},
address={Berlin},
author={Tom Croonenborghs and Karl Tuyls and Jan Ramon and Maurice Bruynooghe},
bib2html_pubtype={Book Chapter},
bib2html_rescat={Multi-Agent Learning},
booktitle={Learning and Adaptation in Multi-Agent Systems},
editor={K. Tuyls and P.J. {'t Hoen} and K. Verbeeck and S. Sen},
file={H\:\\Documents\\TU\\jaar 5\\IN 5010 - research project\\achtergrond\\reinforcement learning\\Croonbook06.pdf:H\:\\Documents\\TU\\jaar 5\\IN 5010 - research project\\achtergrond\\reinforcement learning\\Croonbook06.pdf:PDF},
pages={198-212},
publisher={Springer Verlag},
series={Lecture Notes in Artificial Intelligence},
title={{M}ulti-{A}gent {R}elational {R}einforcement {L}earning. {E}xplorations in {M}ulti-{S}tate {C}oordination {T}asks},
volume=3898, year=2006, }
-
L. Panait, K. Sullivan, and S. Luke, Lenience Towards Teammates Helps in Cooperative Multiagent Learning, in Proc. of 5th Intl. Conf. on Autonomous Agents and Multiagent Systems (AAMAS 2006), 2006.
@inproceedings{Panait2006,
author={L. Panait and K. Sullivan and S. Luke},
booktitle={Proc. of 5th Intl. Conf. on Autonomous Agents and Multiagent Systems (AAMAS 2006)},
editor={Nakashima and Wellman and Weiss and Stone},
title={{L}enience {T}owards {T}eammates {H}elps in {C}ooperative {M}ultiagent {L}earning},
year=2006, }
-
N. Lemmens, To bee or not to bee: A comparitive study in Swarm Intelligence, Master’s Dissertation , 2006.
@mastersthesis{Lemmens06,
author={Nyree Lemmens},
file={Lemmens06.pdf:Personal Publications\\Lemmens06.pdf:PDF;Lemmens06.pdf:Personal Publications\\Lemmens06.pdf:PDF},
school={Universiteit Maastricht, The Netherlands},
title={To bee or not to bee: A comparitive study in Swarm Intelligence},
year=2006, }
-
S. de Jong, K. Tuyls, T. Hashimoto, and H. Iida, Scalable Potential-Field Multi-Agent Coordination in Resource Distribution Tasks, in Proceedings of the AAMAS 2006 Workshop on Adaptation and Learning in Autonomous Agents and Multiagent Systems, Hakodate, Hokkaido, Japan, 2006.
@inproceedings{Jong2006c, address={Hakodate, Hokkaido, Japan},
author={Steven de Jong and Karl Tuyls and Tsuyoshi Hashimoto and Hiroyuki Iida},
booktitle={Proceedings of the AAMAS 2006 Workshop on Adaptation and Learning in Autonomous Agents and Multiagent Systems},
editor={Liviu Panait and Sandip Sen and Eduardo Alonso},
month={May 8th},
title={{S}calable {P}otential-{F}ield {M}ulti-{A}gent {C}oordination in {R}esource {D}istribution {T}asks},
url={http://dl.dropbox.com/u/1505034/website/publications/alaamas-main.pdf},
year=2006, }
-
S. de Jong, K. Tuyls, and I. Sprinkhuizen-Kuyper, Nature-Inspired Multi-Agent Coordination in Task Assignment Problems, in Proceedings of the 6th European Symposium on Adaptive Learning Agents and MAS (ALAMAS), 2006.
@inproceedings{Jong2006b,
author={Steven de Jong and Karl Tuyls and Ida Sprinkhuizen-Kuyper},
booktitle={Proceedings of the 6th European Symposium on Adaptive Learning Agents and MAS (ALAMAS)},
editor={Ann Nowe and Maarten Peeters and Katja Verbeeck},
title={{N}ature-{I}nspired {M}ulti-{A}gent {C}oordination in {T}ask {A}ssignment {P}roblems},
url={http://dl.dropbox.com/u/1505034/website/publications/alamas-main.pdf},
year=2006, }
-
P. J. ‘t. Hoen, K. Tuyls, L. Panait, S. Luke, and H. la Poutré, An Overview of Cooperative and Competitive Multiagent Learning, , Tuyls, K., Hoen, P. J. ‘t., Verbeeck, K., and Sen, S., Eds., Springer LNAI 3898, 2006, pp. 1-50.
@incollection{Hoen2006,
author={P.J. 't Hoen and K. Tuyls and L. Panait and S. Luke and H. la Poutr\'e},
booktitle={Learning and Adaptation in Multi-Agent Systems},
editor={K. Tuyls and P.J. 't Hoen and K. Verbeeck and S. Sen},
pages={1--50},
publisher={Springer LNAI 3898},
title={{A}n {O}verview of {C}ooperative and {C}ompetitive {M}ultiagent {L}earning},
url={http://www.springerlink.com/index/01874X5207852417.pdf},
year=2006, }
-
G. Chaslot, S. de Jong, J. Saito, and J. Uiterwijk, Monte-Carlo Tree Search in Production Management Problems, in Proceedings of BNAIC 2006, 2006.
@inproceedings{Chaslot2006,
author={Guillaume Chaslot and Steven de Jong and Jahn-Takeshi Saito and Jos Uiterwijk},
booktitle={Proceedings of BNAIC 2006},
title={{M}onte-{C}arlo {T}ree {S}earch in {P}roduction {M}anagement {P}roblems},
year=2006, }
-
K. Tuyls and A. Nowe, Evolutionary Game Theory and Multi-Agent Reinforcement Learning., The Knowledge Engineering Review, vol. 20, pp. 63-90, 2005.
@article{Tuyls2005a,
author={Tuyls, K. and Nowe, A.},
issue=01, journal={The Knowledge Engineering Review},
pages={63-90},
title={{E}volutionary {G}ame {T}heory and {M}ulti-{A}gent {R}einforcement {L}earning.},
volume=20, year=2005, }
-
B. Torben Nielsen and S. de Jong, Biologically realistic self-repair applied to robotics (extended abstract), in Proceedings of Lerende Oplossingen 2005, Nijmegen, 2005.
@inproceedings{TorbenNielsen2005,
author={Ben {Torben Nielsen} and Steven de Jong},
booktitle={Proceedings of Lerende Oplossingen 2005, Nijmegen},
title={{B}iologically realistic self-repair applied to robotics (extended abstract)},
year=2005, }
-
S. de Jong, P. Spronck, and N. Roos, Requirements for resource management game AI, in Proceedings of the IJCAI 2005 Workshop on Reasoning, Representation, and Learning in Computer Games, 2005.
@inproceedings{dejong2005a,
author={Steven de Jong and Pieter Spronck and Nico Roos},
booktitle={Proceedings of the IJCAI 2005 Workshop on Reasoning, Representation, and Learning in Computer Games},
title={Requirements for resource management game AI},
url={http://dl.dropbox.com/u/1505034/website/publications/DeJong2005Reqrmgai.pdf},
year=2005, }
-
K. Verbeeck, Nowe A., and K. Tuyls, Coordinated Exploration in Multi-Agent Reinforcement Learning: An Application to Load-balancing., in Proceedings of the fifth joint conference on autonomous agents and multi-agent systems, Utrecht, The Netherlands, 2005.
@inproceedings{Verbeeck2005a,
author={Verbeeck, K. and Nowe, A., and Tuyls, K.},
booktitle={Proceedings of the fifth joint conference on autonomous agents and multi-agent systems, Utrecht, The Netherlands},
title={{C}oordinated {E}xploration in {M}ulti-{A}gent {R}einforcement {L}earning: {A}n {A}pplication to {L}oad-balancing.},
year=2005, }
-
K. Verbeeck, Nowe A., M. Peeters, and K. Tuyls, Multi-agent reinforcement learning in stochastic single and multi-stage games., in Adaptive Agents and Multi-Agent Systems II, pages 275?294. Springer LNAI 3394, 2005., 2005.
@inproceedings{Verbeeck2005,
author={Verbeeck, K. and Nowe, A., and Peeters, M. and Tuyls, K.},
booktitle={Adaptive Agents and Multi-Agent Systems II, pages 275?294. Springer LNAI 3394, 2005.},
title={{M}ulti-agent reinforcement learning in stochastic single and multi-stage games.},
url={http://www.springerlink.com/index/MFC35DK4C69WMKX4.pdf},
year=2005, }
-
S. de Jong, N. Roos, and I. Sprinkhuizen-Kuyper, Evolutionary planning heuristics in production management, in Proceedings of the BNAIC 2005, 2005.
@inproceedings{dejong2005b,
author={Steven de Jong and Nico Roos and Ida Sprinkhuizen-Kuyper},
booktitle={Proceedings of the BNAIC 2005},
title={Evolutionary planning heuristics in production management},
url={http://dl.dropbox.com/u/1505034/website/publications/DeJong2005EPH.pdf},
year=2005, }
