VOCE: Variational Optimization with Conservative Estimation for Offline Safe Reinforcement Learning.
Jiayi GuanGuang ChenJiaming JiLong YangAo ZhouZhijun LiChangjun JiangPublished in: NeurIPS (2023)
Keyphrases
- reinforcement learning
- global optimization
- optimization problems
- machine learning
- function approximation
- optimization algorithm
- model free
- optimization method
- data sets
- methods in computer vision
- optimal policy
- multi agent
- least squares
- state space
- density estimation
- optimization methods
- image processing
- variational methods
- policy search
- real time
- robotic control