BAIL: Best-Action Imitation Learning for Batch Deep Reinforcement Learning.
Xinyue ChenZijian ZhouZheng WangChe WangYanqiu WuQing DengKeith W. RossPublished in: CoRR (2019)
Keyphrases
- imitation learning
- reinforcement learning
- action selection
- action space
- function approximation
- reinforcement learning methods
- learning algorithm
- mirror neurons
- reinforcement learning algorithms
- multi agent
- temporal difference
- state space
- control problems
- optimal policy
- optimal control
- markov decision process
- multi modal
- machine learning
- learning problems
- humanoid robot
- maximum margin
- markov decision processes