Enhancing Off-Policy Constrained Reinforcement Learning through Adaptive Ensemble C Estimation.
Hengrui ZhangYoufang LinShuo ShenSheng HanKai LvPublished in: AAAI (2024)
Keyphrases
- reinforcement learning
- learning algorithm
- neural network
- temporal difference
- state space
- parameter estimation
- machine learning
- training set
- adaptive control
- estimation algorithm
- optimal control
- decision directed
- robotic control
- estimation process
- action selection
- random forests
- ensemble methods
- transfer learning
- optimal policy
- prediction accuracy
- dynamic programming
- learning process
- decision trees
- feature selection