Entropy Maximization for Markov Decision Processes Under Temporal Logic Constraints.
Yagiz SavasMelkior OrnikMurat CubuktepeMustafa O. KarabagUfuk TopcuPublished in: IEEE Trans. Autom. Control. (2020)
Keyphrases
- markov decision processes
- temporal logic
- model checking
- automata theoretic
- dynamic constraints
- state space
- optimal policy
- finite state
- reachability analysis
- modal logic
- dynamic programming
- reinforcement learning
- transition matrices
- reinforcement learning algorithms
- average cost
- policy iteration
- average reward
- planning under uncertainty
- decision theoretic planning
- partially observable
- verification method
- decision processes
- infinite horizon
- computation tree logic
- action sets
- markov decision process
- stochastic shortest path
- linear temporal logic
- temporally extended
- reward function
- heuristic search
- objective function