Structured Reachability Analysis for Markov Decision Processes.
Craig BoutilierRonen I. BrafmanChristopher W. GeibPublished in: UAI (1998)
Keyphrases
- reachability analysis
- markov decision processes
- state space
- optimal policy
- finite state
- policy iteration
- reinforcement learning
- model checking
- transition matrices
- dynamic programming
- incremental algorithms
- partially observable
- reinforcement learning algorithms
- decision theoretic planning
- average cost
- model based reinforcement learning
- average reward
- planning under uncertainty
- markov decision process
- state and action spaces
- infinite horizon
- action space
- timed automata
- reward function