Offline Reinforcement Learning with Closed-Form Policy Improvement Operators.
Jiachen LiEdwin ZhangMing YinQinxun BaiYu-Xiang WangWilliam Yang WangPublished in: ICML (2023)
Keyphrases
- generalized gaussian density
- closed form
- reinforcement learning
- optimal policy
- policy search
- action selection
- markov decision process
- function approximators
- state space
- point correspondences
- closed form solutions
- function approximation
- markov decision processes
- reward function
- reinforcement learning algorithms
- action space
- dynamic programming
- iterative procedure
- closed form expressions
- model free
- motion estimation
- control policy
- multiresolution