Competitive Markov decision processes with partial observation.
Shun-Pin HsuAristotle ArapostathisPublished in: SMC (1) (2004)
Keyphrases
- markov decision processes
- state space
- optimal policy
- finite state
- reinforcement learning
- transition matrices
- policy iteration
- dynamic programming
- factored mdps
- model based reinforcement learning
- decision theoretic planning
- planning under uncertainty
- average reward
- reachability analysis
- decision processes
- partially observable
- finite horizon
- average cost
- reinforcement learning algorithms
- infinite horizon
- markov decision process
- reward function
- action sets
- real time dynamic programming
- risk sensitive
- action space
- multi agent