Limiting Average Criteria For Nonstationary Markov Decision Processes.
Xianping GuoPeng ShiPublished in: SIAM J. Optim. (2001)
Keyphrases
- markov decision processes
- non stationary
- average cost
- finite horizon
- discounted reward
- finite state
- optimal policy
- state space
- transition matrices
- policy iteration
- reinforcement learning
- random fields
- decision theoretic planning
- reinforcement learning algorithms
- dynamic programming
- stationary policies
- reachability analysis
- planning under uncertainty
- partially observable
- markov decision process
- action sets
- average reward
- model based reinforcement learning
- infinite horizon
- factored mdps
- state and action spaces
- action space
- optimal control
- multistage
- long run
- decision making