On Exact Embedding Framework for Optimal Control of Markov Decision Processes.
Sonam KharadeSarang SutavaniAmol YerudkarSushama WaghYang LiuCarmen Del VecchioNavdeep M. SinghPublished in: IEEE Trans. Autom. Control. (2024)
Keyphrases
- markov decision processes
- optimal control
- risk sensitive
- infinite horizon
- dynamic programming
- decision theoretic planning
- reinforcement learning
- policy iteration
- average cost
- optimal policy
- state space
- transition matrices
- finite state
- optimal control problems
- control strategy
- planning under uncertainty
- reinforcement learning algorithms
- action space
- adaptive control
- lead time
- control problems
- markov decision process
- finite horizon
- action sets
- policy iteration algorithm