A Counterexample Guided Abstraction-Refinement Framework for Markov Decision Processes
Rohit ChadhaMahesh ViswanathanPublished in: CoRR (2008)
Keyphrases
- markov decision processes
- decision theoretic planning
- transition matrices
- state space
- decision processes
- planning under uncertainty
- average reward
- finite horizon
- reinforcement learning algorithms
- finite state
- optimal policy
- reinforcement learning
- reachability analysis
- model based reinforcement learning
- dynamic programming
- policy iteration
- reward function
- risk sensitive
- state and action spaces
- semi markov decision processes