Learning sequences of actions in collectives of autonomous agents

Proceedings of the International Conference on Autonomous Agents

Volumn , Issue 2, 2002, Pages 378-385

  Tumer, Kagan ^a   Agogino, Adrian K ^a   Wolpert, David H ^a  

^a NASA AMES RESEARCH CENTER   (United States)

Author keywords

MAS; Q learning; Reinforcement learning

Indexed keywords

ALGORITHMS; LEARNING SYSTEMS; MULTI AGENT SYSTEMS; SIGNAL TO NOISE RATIO;

LEARNING SEQUENCES;

AUTONOMOUS AGENTS;

EID: 0036355687     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1145/544741.544832     Document Type: Conference Paper

References (24)

1. Multiagent systems: Challenges and opportunities for decision theoretic planning
2. Packet routing in dynamically changing networks: A reinforcement learning approach
3. The dynamics of reinforcement learning cooperative multiagent systems
4. Improving elevator performance using reinforcement learning
5. Learning in network contexts: Experimental results from simulations
6. Incentives in teams
7. The tragedy of the commons
8. Multiagent reinforcement learning: Theoretical framework and an algorithm
9. A roadmap of agent research and development
10. Multiagent reinforcement learning in the iterated prisoner's dilemma
11. Multiagent systems: A survey from a machine learning perspective
12. Collective intelligence and Braess' paradox
13. Counterspeculation, auctions and competitive sealed tenders
14. Q-learning
15. A market-oriented programming environment and its application to distributed multicommodity flow problems
16. Adaptivity in agent-based routing for data networks
17. An introduction to collective intelligence
18. Optimal payoff functions for members of collectives
19. Using collective intelligence to route internet traffic
20. Collective intelligence for control of distributed dynamical systems
21. Solving combinatorial optimization tasks by reinforcement learning: A general methodology applied to resource-constrained scheduling