Counterexample Explanation by Learning Small Strategies in Markov Decision Processes.
Tomás BrázdilKrishnendu ChatterjeeMartin ChmelikAndreas FellnerJan KretínskýPublished in: CAV (1) (2015)
Keyphrases
- markov decision processes
- reinforcement learning
- optimal policy
- learning algorithm
- stochastic games
- model based reinforcement learning
- transition matrices
- state space
- explanation based learning
- finite state
- state abstraction
- decision theoretic planning
- infinite horizon
- reinforcement learning algorithms
- partially observable
- average cost
- risk sensitive
- reachability analysis
- monte carlo