In-sample Actor Critic for Offline Reinforcement Learning.
Hongchang ZhangYixiu MaoBoyuan WangShuncheng HeYi XuXiangyang JiPublished in: ICLR (2023)
Keyphrases
- actor critic
- reinforcement learning
- temporal difference
- policy gradient
- reinforcement learning algorithms
- approximate dynamic programming
- optimal control
- function approximation
- gradient method
- neuro fuzzy
- state space
- model free
- policy iteration
- markov decision processes
- control problems
- natural actor critic
- rl algorithms
- average reward
- learning algorithm
- monte carlo
- optimal policy
- supervised learning
- machine learning
- recurrent neural networks
- learning problems
- dynamical systems
- action space
- transfer learning
- temporal difference learning
- sample size
- dynamic programming
- policy gradient methods