Monte Carlo Tree Search for Verifying Reachability in Markov Decision Processes.
Pranav AshokTomás BrázdilJan KretínskýOndrej SlámeckaPublished in: ISoLA (2) (2018)
Keyphrases
- markov decision processes
- monte carlo tree search
- state space
- monte carlo
- reinforcement learning algorithms
- reinforcement learning methods
- optimal policy
- evaluation function
- markov chain
- reinforcement learning
- finite state
- dynamic programming
- transition matrices
- temporal difference learning
- average reward
- particle filter
- temporal difference
- policy iteration
- average cost
- markov decision process
- infinite horizon
- heuristic search
- action space
- partially observable
- model checking
- decision theoretic planning
- game tree
- belief state
- planning problems
- least squares