Harnessing Density Ratios for Online Reinforcement Learning.
Philip AmortilaDylan J. FosterNan JiangAyush SekhariTengyang XiePublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- online learning
- real time
- function approximation
- state space
- machine learning
- multi agent
- supervised learning
- balancing exploration and exploitation
- robotic control
- temporal difference learning
- reinforcement learning algorithms
- collective intelligence
- collaborative learning
- information retrieval
- data mining
- real world