Blessing from Experts: Super Reinforcement Learning in Confounded Environments.
Jiayi WangZhengling QiChengchun ShiPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- multi agent environments
- model free
- function approximation
- learning algorithm
- markov decision processes
- optimal policy
- state space
- dynamic environments
- multi agent
- human experts
- artificial intelligence
- temporal difference
- temporal difference learning
- learning process
- multi agent systems
- statistically significant
- transfer learning
- search engine
- optimal control
- control policy
- autonomous learning
- real world