Constrained Markov decision processes with first passage criteria.
Yonghui HuangQingda WeiXianping GuoPublished in: Ann. Oper. Res. (2013)
Keyphrases
- markov decision processes
- finite state
- state space
- optimal policy
- reachability analysis
- dynamic programming
- reinforcement learning algorithms
- transition matrices
- reinforcement learning
- decision theoretic planning
- planning under uncertainty
- factored mdps
- partially observable
- average reward
- decision processes
- risk sensitive
- policy iteration
- action space
- finite horizon
- average cost
- infinite horizon
- decision diagrams
- fixed point
- decision problems
- discounted reward
- multistage
- markov chain
- stochastic shortest path