A multiagent reinforcement learning algorithm by dynamically merging Markov decision processes

Proceedings of the International Conference on Autonomous Agents

Volumn , Issue 1, 2002, Pages 845-846

  Ghavamzadeh, Mohammad ^a   Mahadevan, Sridhar ^a  

^a Biologically Inspired Neural and Dynamical Systems Laboratory   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHMS; ARTIFICIAL INTELLIGENCE; DECISION MAKING; LEARNING SYSTEMS; MARKOV PROCESSES;

MARKOV DECISION PROCESSES (MDP);

MULTI AGENT SYSTEMS;

EID: 0036368749     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1145/544862.544940     Document Type: Conference Paper

References (3)

1. Sequential optimality and coordination in multiagent systems
2. How to dynamically merge markov decision processes