Markov decision processes with exponentially representable discounting.
Yair CarmonAdam ShwartzPublished in: Oper. Res. Lett. (2009)
Keyphrases
- markov decision processes
- state space
- finite state
- reinforcement learning
- optimal policy
- transition matrices
- dynamic programming
- reinforcement learning algorithms
- policy iteration
- markov decision process
- risk sensitive
- planning under uncertainty
- infinite horizon
- finite horizon
- action space
- decision processes
- reachability analysis
- factored mdps
- average reward
- model based reinforcement learning
- decision theoretic planning
- partially observable
- state and action spaces
- action sets
- discounted reward
- policy evaluation
- probabilistic planning
- average cost