A Perspective of Q-value Estimation on Offline-to-Online Reinforcement Learning.
Yinmin ZhangJie LiuChuming LiYazhe NiuYaodong YangYu LiuWanli OuyangPublished in: AAAI (2024)
Keyphrases
- reinforcement learning
- real time
- online learning
- accurate estimation
- estimation algorithm
- function approximation
- machine learning
- online environment
- model free
- parameter estimation
- state space
- learning process
- viewpoint
- maximum likelihood estimation
- learning algorithm
- multi agent reinforcement learning
- multi agent
- objective function
- image sequences
- search engine
- batch mode
- robotic control