Expert-Supervised Reinforcement Learning for Offline Policy Learning and Evaluation.
Aaron Sonabend W.Junwei LuLeo A. CeliTianxi CaiPeter SzolovitsPublished in: CoRR (2020)
Keyphrases
- reinforcement learning
- learning algorithm
- learning process
- supervised learning
- inverse reinforcement learning
- unsupervised learning
- partially observable environments
- learning systems
- active learning
- partially observable
- domain knowledge
- state space
- semi supervised
- online learning
- training data
- action selection
- prior knowledge
- function approximation
- learning capabilities
- reinforcement learning methods
- autonomous learning
- actor critic
- feature selection
- machine learning