Markov decision processes with a stopping time constraint.
Masayuki HoriguchiPublished in: Math. Methods Oper. Res. (2001)
Keyphrases
- markov decision processes
- optimal policy
- reinforcement learning
- state space
- finite state
- dynamic programming
- transition matrices
- policy iteration
- finite horizon
- average cost
- action space
- planning under uncertainty
- reachability analysis
- partially observable
- markov decision process
- risk sensitive
- infinite horizon
- factored mdps
- decision theoretic planning
- average reward
- decision processes
- decision diagrams
- state and action spaces
- model based reinforcement learning
- action sets
- reinforcement learning algorithms
- reward function