KoGuN: Accelerating Deep Reinforcement Learning via Integrating Human Suboptimal Knowledge.
Peng ZhangJianye HaoWeixun WangHongyao TangYi MaYihai DuanYan ZhengPublished in: IJCAI (2020)
Keyphrases
- reinforcement learning
- domain knowledge
- knowledge sharing
- human experts
- expert systems
- human interaction
- knowledge representation
- human knowledge
- human users
- knowledge transfer
- function approximation
- optimal policy
- knowledge acquisition
- knowledge management
- knowledge discovery
- prior knowledge
- model free
- knowledge extraction
- information systems
- previously learned
- human behavior
- human subjects
- computationally efficient
- knowledge based systems
- knowledge base