Transition-independent decentralized markov decision processes.
Raphen BeckerShlomo ZilbersteinVictor R. LesserClaudia V. GoldmanPublished in: AAMAS (2003)
Keyphrases
- markov decision processes
- decentralized control
- optimal policy
- state space
- finite state
- reinforcement learning
- policy iteration
- dynamic programming
- transition matrices
- reachability analysis
- planning under uncertainty
- factored mdps
- decision processes
- finite horizon
- partially observable
- decision theoretic planning
- average cost
- cooperative
- multi agent
- action space
- model based reinforcement learning
- state abstraction
- stochastic games
- average reward
- reinforcement learning algorithms
- reward function
- infinite horizon
- risk sensitive
- semi markov decision processes
- decision diagrams
- transition model
- dec pomdps
- dynamical systems
- monte carlo
- least squares
- interval estimation