Active Learning of Markov Decision Processes for System Verification.
Yingke ChenThomas Dyhre NielsenPublished in: ICMLA (2) (2012)
Keyphrases
- markov decision processes
- active learning
- state space
- optimal policy
- finite state
- reinforcement learning
- model checking
- dynamic programming
- policy iteration
- planning under uncertainty
- learning algorithm
- transition matrices
- reinforcement learning algorithms
- partially observable
- reachability analysis
- decision processes
- finite horizon
- model based reinforcement learning
- factored mdps
- decision theoretic planning
- risk sensitive
- markov decision process
- average cost
- semi supervised
- machine learning
- supervised learning
- action space
- action sets
- average reward
- state and action spaces
- training set
- heuristic search
- learning process
- transfer learning
- discounted reward
- semi markov decision processes