Optimal Control of Markov Decision Processes With Linear Temporal Logic Constraints.
Xu Chu DingStephen L. SmithCalin BeltaDaniela RusPublished in: IEEE Trans. Autom. Control. (2014)
Keyphrases
- optimal control
- markov decision processes
- dynamic programming
- risk sensitive
- linear temporal logic
- infinite horizon
- reinforcement learning
- policy iteration
- average cost
- control problems
- optimal policy
- finite state
- state space
- control strategy
- model checking
- policy iteration algorithm
- reinforcement learning algorithms
- temporal logic
- decision theoretic planning
- transition matrices
- finite horizon
- partially observable
- action space
- multistage
- average reward
- production planning
- markov decision process
- decision problems
- linear programming
- machine learning