Harnessing Density Ratios for Online Reinforcement Learning.
Philip AmortilaDylan J. FosterNan JiangAyush SekhariTengyang XiePublished in: ICLR (2024)
Keyphrases
- reinforcement learning
- function approximation
- online learning
- real time
- learning process
- machine learning
- optimal control
- information retrieval
- learning algorithm
- artificial intelligence
- state space
- markov decision processes
- online environment
- reinforcement learning algorithms
- swarm intelligence
- optimal policy
- neural network