PAC Statistical Model Checking for Markov Decision Processes and Stochastic Games.
Pranav AshokJan KretínskýMaximilian WeiningerPublished in: CAV (1) (2019)
Keyphrases
- markov decision processes
- stochastic games
- model checking
- reachability analysis
- finite state
- average reward
- state space
- optimal policy
- multiagent reinforcement learning
- reinforcement learning algorithms
- reinforcement learning
- policy iteration
- dynamic programming
- decision theoretic planning
- average cost
- infinite horizon
- finite state machines
- partially observable
- finite horizon
- long run
- action space
- learning algorithm
- planning domains
- nash equilibria
- decision problems
- cooperative
- timed automata