Ensemble Successor Representations for Task Generalization in Offline-to-Online Reinforcement Learning.
Changhong WangXudong YuChenjia BaiQiaosheng ZhangZhen WangPublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- online learning
- function approximation
- ensemble learning
- neural network
- learning algorithm
- ensemble methods
- real time
- state space
- function approximators
- higher level
- training data
- machine learning
- dynamic programming
- training set
- multi agent
- decision trees
- website
- random forests
- symbolic representation
- learning machines
- robotic control
- balancing exploration and exploitation