Non-linear dynamics in multiagent reinforcement learning algorithms

Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS

Volumn 3, Issue , 2008, Pages 1293-1296

  Abdallah, Sherief ^a   Lesser, Victor ^b  

^a THE BRITISH UNIVERSITY IN DUBAI   (United Arab Emirates)

^b UNIVERSITY OF MASSACHUSETTS   (United States)

Author keywords

Convergence analysis; Dynamics; Multiagent systems; Reinforcement learning

Indexed keywords

AUTONOMOUS AGENTS; DIFFERENTIAL EQUATIONS; DYNAMICS; FERTILIZERS; MULTI AGENT SYSTEMS; PROBABILITY DISTRIBUTIONS; REINFORCEMENT LEARNING;

CONVERGENCE ANALYSIS; LINEAR DYNAMICS; MULTIAGENT REINFORCEMENT LEARNING ALGORITHM; NON-LINEAR DYNAMICS; STOCHASTIC POLICY;

ALGORITHMS;

EID: 84899897951     PISSN: 15488403     EISSN: 15582914     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (4)

1. Singh, S., Kearns, M., Mansour, Y.: Nash convergence of gradient dynamics in general-sum games. In: the 16th Conference on Uncertainty in Artificial Intelligence. (2000) 541-548
2. Abdallah, S., Lesser, V.: Learning the task allocation game. In: Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems (AAMAS). (2006)
3. Zinkevich, M.: Online convex programming and generalized infinitesimal gradient ascent. In: Proceedings of the International Conference on Machine Learning. (2003) 928-936
4. Bowling, M., Veloso, M.: Multiagent learning using a variable learning rate. Artificial Intelligence 136(2) (2002) 215-250