Bridging Offline Reinforcement Learning and Imitation Learning: A Tale of Pessimism.
Paria RashidinejadBanghua ZhuCong MaJiantao JiaoStuart RussellPublished in: NeurIPS (2021)
Keyphrases
- imitation learning
- reinforcement learning
- reinforcement learning methods
- function approximation
- reinforcement learning algorithms
- real time
- state space
- markov decision processes
- control problems
- machine learning
- action selection
- robotic systems
- learning problems
- optimal policy
- training samples
- learning algorithm
- dynamical systems
- learning classifier systems
- maximum margin
- temporal difference
- supervised learning
- dynamic programming
- action space
- learning process