Model-Based Offline Meta-Reinforcement Learning with Regularization.
Sen LinJialin WanTengyu XuYingbin LiangJunshan ZhangPublished in: ICLR (2022)
Keyphrases
- reinforcement learning
- model free
- reinforcement learning algorithms
- function approximation
- learning algorithm
- temporal difference
- multi agent
- dynamic programming
- state space
- parameter selection
- markov decision processes
- data driven
- supervised learning
- learning process
- prior information
- robotic control
- regularization methods
- policy search
- real time
- meta level
- data dependent
- optimal control
- image segmentation
- clustering algorithm
- neural network