Entropy Maximization for Markov Decision Processes Under Temporal Logic Constraints.
Yagiz SavasMelkior OrnikMurat CubuktepeUfuk TopcuPublished in: CoRR (2018)
Keyphrases
- markov decision processes
- temporal logic
- model checking
- finite state
- automata theoretic
- dynamic constraints
- reachability analysis
- optimal policy
- state space
- modal logic
- policy iteration
- transition matrices
- dynamic programming
- reinforcement learning
- model based reinforcement learning
- decision theoretic planning
- verification method
- computation tree logic
- reinforcement learning algorithms
- markov decision process
- planning under uncertainty
- partially observable
- linear temporal logic
- infinite horizon
- temporally extended
- belief revision
- average cost
- average reward
- decision processes
- action space
- objective function
- action sets