Solution Procedures for Partially Observed Markov Decision Processes.
Chelsea C. White IIIWilliam T. SchererPublished in: Oper. Res. (1989)
Keyphrases
- partially observed
- markov decision processes
- expected reward
- state space
- finite state
- optimal policy
- reinforcement learning
- policy iteration
- dynamic programming
- planning under uncertainty
- transition matrices
- factored mdps
- average cost
- finite horizon
- risk sensitive
- decision processes
- partially observable
- infinite horizon
- reachability analysis
- average reward
- reinforcement learning algorithms
- action space
- model based reinforcement learning
- markov decision process
- dynamical systems
- reward function
- state and action spaces
- action sets