Learning and Adaption in Multi-Agent Systems

1. Front Matter

   PDF

2. An Overview of Cooperative and Competitive Multiagent Learning

   • Pieter Jan ’t Hoen, Karl Tuyls, Liviu Panait, Sean Luke, J. A. La Poutré

   Pages 1-46

3. Multi-robot Learning for Continuous Area Sweeping

   • Mazda Ahmadi, Peter Stone

   Pages 47-70

4. Learning Automata as a Basis for Multi Agent Reinforcement Learning

   • Ann Nowé, Katja Verbeeck, Maarten Peeters

   Pages 71-85

5. Learning Pareto-optimal Solutions in 2x2 Conflict Games

   • Stéphane Airiau, Sandip Sen

   Pages 86-99

6. Unifying Convergence and No-Regret in Multiagent Learning

   • Bikramjit Banerjee, Jing Peng

   Pages 100-114

7. Implicit Coordination in a Network of Social Drivers: The Role of Information in a Commuting Scenario

   • Ana L. C. Bazzan, Manuel Fehler, Franziska Klügl

   Pages 115-128

8. Multiagent Traffic Management: Opportunities for Multiagent Learning

   • Kurt Dresner, Peter Stone

   Pages 129-138

9. Dealing with Errors in a Cooperative Multi-agent Learning System

   • Constança Oliveira e Sousa, Luis Custódio

   Pages 139-154

10. The Success and Failure of Tag-Mediated Evolution of Cooperation

    • Austin McDonald, Sandip Sen

    Pages 155-164

11. An Adaptive Approach for the Exploration-Exploitation Dilemma and Its Application to Economic Systems

    • Lilia Rejeb, Zahia Guessoum, Rym M’Hallah

    Pages 165-176

12. Efficient Reward Functions for Adaptive Multi-rover Systems

    • Kagan Tumer, Adrian Agogino

    Pages 177-191

13. Multi-agent Relational Reinforcement Learning

    • Tom Croonenborghs, Karl Tuyls, Jan Ramon, Maurice Bruynooghe

    Pages 192-206

14. Multi-type ACO for Light Path Protection

    • Peter Vrancx, Ann Nowé, Kris Steenhaut

    Pages 207-215

15. Back Matter

    PDF

This book contains selected and revised papers of the International Workshop on Lea- ing and Adaptation in Multi-Agent Systems (LAMAS 2005), held at the AAMAS 2005 Conference in Utrecht, The Netherlands, July 26. An important aspect in multi-agent systems (MASs) is that the environment evolves over time, not only due to external environmental changes but also due to agent int- actions. For this reason it is important that an agent can learn, based on experience, and adapt its knowledge to make rational decisions and act in this changing environment autonomously. Machine learning techniques for single-agent frameworks are well established. Agents operate in uncertain environments and must be able to learn and act - tonomously. This task is, however, more complex when the agent interacts with other agents that have potentially different capabilities and goals. The single-agent case is structurally different from the multi-agent case due to the added dimension of dynamic interactions between the adaptive agents. Multi-agent learning, i.e., the ability of the agents to learn how to cooperate and compete, becomes crucial in many domains. Autonomous agents and multi-agent systems (AAMAS) is an emerging multi-disciplinary area encompassing computer science, software engineering, biology, as well as cognitive and social sciences. A t- oretical framework, in which rationality of learning and interacting agents can be - derstood, is still under development in MASs, although there have been promising ?rst results.

• Evolution
• adaptive agents
• agent communication
• agent coordination
• agent environments
• agent programming
• agent reasoning
• agents
• distributed artificial intelligence
• learning
• machine learning
• multi-agent learning systems
• multi-agent system
• reinforcement learning
• robot

• MICC-IKAT, Universiteit Maastricht, The Netherlands

  Karl Tuyls

• Center for Mathematics and Computer Science (CWI), Amsterdam, The Netherlands

  Pieter Jan’t Hoen

• KaHo Sint-Lieven, Information Technology Group, Gent, Belgium

  Katja Verbeeck

• Department of Mathematical and Computer Science, University of Tulsa, USA

  Sandip Sen

Policies and ethics