Context-Adapted Multi-policy Ensemble Method for Generalization in Reinforcement Learning.
Tingting XuFengge WuJunsuo ZhaoPublished in: ICONIP (1) (2022)
Keyphrases
- ensemble methods
- reinforcement learning
- prediction accuracy
- optimal policy
- random forest
- machine learning methods
- random forests
- rotation forest
- policy search
- ensemble learning
- reward function
- decision trees
- learning algorithm
- benchmark datasets
- base classifiers
- generalization ability
- classifier ensemble
- text classification
- supervised learning
- semi supervised
- state space
- function approximation
- machine learning
- neural network