A multiagent reinforcement learning algorithm using extended optimal response

Proceedings of the International Conference on Autonomous Agents

Volumn , Issue 2, 2002, Pages 370-377

  Suematsu, Nobuo ^a   Hayashi, Akira ^a  

^a HIROSHIMA CITY UNIVERSITY   (Japan)

Author keywords

Markov games; Q learning; Reinforcement learning; Stochastic games

Indexed keywords

DYNAMIC PROGRAMMING; LEARNING ALGORITHMS; MARKOV PROCESSES; RANDOM PROCESSES;

STOCHASTIC GAMES;

MULTI AGENT SYSTEMS;

EID: 0036355732     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1145/544829.544831     Document Type: Conference Paper

References (14)

1. Convergence problems of general-sum multiagent reinforcement learning
2. Rational and convergent learning in stochastic games
3. The dynamics of reinforcement learning in cooperative multiagent systems
4. Multiagent reinforcement learning: Theoretical framework and an algorithm
5. Experimental results on q-learning for general-sum stochastic games
6. Markov games as a framework for multi-agent reinforcement learning
7. Value-function reinforcement learning in Markov games
8. Non-cooperative games
9. A stochastic approximation method
10. Multiagent systems: A survey from a machine learning perspective