ENOTO: Improving Offline-to-Online Reinforcement Learning with Q-Ensembles.
Kai ZhaoJianye HaoYi MaJinyi LiuYan ZhengZhaopeng MengPublished in: AAMAS (2024)
Keyphrases
- reinforcement learning
- real time
- learning algorithm
- function approximation
- decision trees
- state space
- online learning
- temporal difference
- reinforcement learning algorithms
- balancing exploration and exploitation
- multi class
- markov decision processes
- ensemble methods
- ensemble learning
- learning classifier systems
- temporal difference learning