Incremental quantitative verification for Markov decision processes.
Marta Z. KwiatkowskaDavid ParkerHongyang QuPublished in: DSN (2011)
Keyphrases
- markov decision processes
- finite state
- optimal policy
- policy iteration
- state space
- reinforcement learning
- transition matrices
- dynamic programming
- model checking
- risk sensitive
- finite horizon
- reachability analysis
- reinforcement learning algorithms
- decision processes
- decision theoretic planning
- factored mdps
- partially observable
- model based reinforcement learning
- planning under uncertainty
- action space
- average reward
- infinite horizon
- incremental algorithms
- data mining
- markov decision process
- average cost
- markov chain