3 papers
cs.LG2024
Any-step Dynamics Model Improves Future Predictions for Online and Offline Reinforcement Learning
Haoxin Lin, Yu-Yan Xu, Yihao Sun +6
Model-based methods in reinforcement learning offer a promising approach to enhance data efficiency by facilitating policy exploration within a dynamics model. However, accurately…
cs.LG2024
Knowledgeable Agents by Offline Reinforcement Learning from Large Language Model Rollouts
Jing-Cheng Pang, Si-Hang Yang, Kaiyuan Li +4
Reinforcement learning (RL) trains agents to accomplish complex tasks through environmental interaction data, but its capacity is also limited by the scope of the available data. T…
cs.LG2023
Episodic Return Decomposition by Difference of Implicitly Assigned Sub-Trajectory Reward
Haoxin Lin, Hongqiu Wu, Jiaji Zhang +3
Real-world decision-making problems are usually accompanied by delayed rewards, which affects the sample efficiency of Reinforcement Learning, especially in the extremely delayed c…