Trace Refinement in Labelled Markov Decision Processes.
Nathanaël FijalkowStefan KieferMahsa ShirmohammadiPublished in: CoRR (2015)
Keyphrases
- markov decision processes
- optimal policy
- state space
- finite state
- reinforcement learning
- policy iteration
- dynamic programming
- decision theoretic planning
- transition matrices
- reachability analysis
- factored mdps
- action space
- average cost
- risk sensitive
- average reward
- markov decision process
- reward function
- planning under uncertainty
- decision processes
- finite horizon
- reinforcement learning algorithms
- infinite horizon
- partially observable
- action sets
- total reward
- discounted reward
- state and action spaces
- markov chain