Bridging Imitation and Online Reinforcement Learning: An Optimistic Tale.
Botao HaoRahul JainDengwang TangZheng WenPublished in: Trans. Mach. Learn. Res. (2023)
Keyphrases
- reinforcement learning
- function approximation
- state space
- online learning
- balancing exploration and exploitation
- markov decision processes
- real time
- supervised learning
- search engine
- learning algorithm
- machine learning
- online communities
- optimal control
- cross cultural
- imitation learning
- database
- website
- information technology
- optimal policy
- batch mode
- stochastic approximation