Reducing Conservativeness Oriented Offline Reinforcement Learning.
Hongchang ZhangJianzhun ShaoYuhang JiangShuncheng HeXiangyang JiPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- function approximation
- reinforcement learning algorithms
- temporal difference
- model free
- real time
- learning algorithm
- optimal policy
- neural network
- learning capabilities
- dynamic programming
- information retrieval
- state space
- optimal control
- significantly reduced
- learning classifier systems
- decision trees
- machine learning
- robot control
- temporal difference learning
- robotic control