Markov Decision Processes with Functional Rewards.
Olivier SpanjaardPaul WengPublished in: MIWAI (2013)
Keyphrases
- markov decision processes
- finite state
- reinforcement learning
- state space
- optimal policy
- dynamic programming
- reachability analysis
- action space
- decision theoretic planning
- average reward
- reward function
- sequential decision making under uncertainty
- transition matrices
- model based reinforcement learning
- partially observable
- policy iteration
- finite horizon
- average cost
- risk sensitive
- reinforcement learning algorithms
- discounted reward
- infinite horizon
- markov decision process
- decision processes
- planning under uncertainty
- multistage
- action sets
- semi markov decision processes
- least squares
- objective function