Structured Reachability Analysis for Markov Decision Processes
Craig BoutilierRonen I. BrafmanChristopher W. GeibPublished in: CoRR (2013)
Keyphrases
- reachability analysis
- markov decision processes
- finite state
- state space
- model checking
- dynamic programming
- policy iteration
- optimal policy
- reinforcement learning
- reinforcement learning algorithms
- average cost
- transition matrices
- decision processes
- planning under uncertainty
- infinite horizon
- partially observable
- incremental algorithms
- action sets
- average reward
- decision theoretic planning
- state and action spaces
- discounted reward
- machine learning
- markov decision process