Communication in Multi-Agent Markov Decision Processes.
Ping XuanVictor R. LesserShlomo ZilbersteinPublished in: ICMAS (2000)
Keyphrases
- markov decision processes
- multi agent
- reinforcement learning
- planning under uncertainty
- state space
- decentralized control
- optimal policy
- finite state
- transition matrices
- dynamic programming
- policy iteration
- decision theoretic planning
- cooperative
- infinite horizon
- model based reinforcement learning
- reinforcement learning algorithms
- reachability analysis
- average cost
- partially observable markov decision processes
- multi agent systems
- finite horizon
- partially observable
- decision processes
- average reward
- action sets
- multiple agents
- factored mdps
- semi markov decision processes
- data mining
- multiagent systems
- state abstraction
- stochastic games
- reward function
- probabilistic planning
- state and action spaces
- action space
- markov decision process
- decision makers