Generalized Policy Iteration for Optimal Control in Continuous Time.
Jingliang DuanShengbo Eben LiZhengyu LiuMonimoy BujarbaruahBo ChengPublished in: CoRR (2019)
Keyphrases
- optimal control
- policy iteration
- optimal control problems
- infinite horizon
- dynamic programming
- control problems
- control strategy
- reinforcement learning
- approximate dynamic programming
- average reward
- average cost
- policy evaluation
- actor critic
- markov decision processes
- brownian motion
- least squares
- policy iteration algorithm
- optimal policy
- finite horizon
- learning algorithm