A counterexample-guided abstraction-refinement framework for markov decision processes.
Rohit ChadhaMahesh ViswanathanPublished in: ACM Trans. Comput. Log. (2010)
Keyphrases
- markov decision processes
- decision theoretic planning
- finite state
- dynamic programming
- state space
- optimal policy
- planning under uncertainty
- policy iteration
- transition matrices
- finite horizon
- model based reinforcement learning
- machine learning
- average cost
- continuous state spaces
- search algorithm
- reachability analysis
- semi markov decision processes
- reinforcement learning