Scalable Verification of Markov Decision Processes.
Axel LegaySean SedwardsLouis-Marie TraonouezPublished in: SEFM Workshops (2014)
Keyphrases
- markov decision processes
- reinforcement learning
- finite state
- policy iteration
- state space
- optimal policy
- transition matrices
- dynamic programming
- reachability analysis
- planning under uncertainty
- model checking
- decision processes
- reinforcement learning algorithms
- decision theoretic planning
- finite horizon
- infinite horizon
- factored mdps
- partially observable
- action space
- markov decision process
- model based reinforcement learning
- average cost
- state and action spaces
- decision diagrams
- risk sensitive
- action sets
- semi markov decision processes
- reward function