Papers › TD3 with Reverse KL Regularizer for Offline Reinforcement Learning from Mixed Datasets

TD3 with Reverse KL Regularizer for Offline Reinforcement Learning from Mixed Datasets

5 Dec 2022arXiv:2212.02125archive 2025-07-28

Yuanying Cai, Chuheng Zhang, Li Zhao, Wei Shen, Xuyun Zhang, Lei Song, Jiang Bian, Tao Qin, TieYan Liu

We consider an offline reinforcement learning (RL) setting where the agent need to learn from a dataset collected by rolling out multiple behavior policies. There are two challenges for this setting: 1) The optimal trade-off between optimizing the RL signal and the behavior cloning (BC) signal changes on different states due to the variation of the action coverage induced by different behavior policies. Previous methods fail to handle this by only controlling the global trade-off. 2) For a given state, the action distribution generated by different behavior policies may have multiple modes. The BC regularizers in many previous methods are mean-seeking, resulting in policies that select out-of-distribution (OOD) actions in the middle of the modes. In this paper, we address both challenges by using adaptively weighted reverse Kullback-Leibler (KL) divergence as the BC regularizer based on the TD3 algorithm. Our method not only trades off the RL and BC signals with per-state weights (i.e., strong BC regularization on the states with narrow action coverage, and vice versa) but also avoids selecting OOD actions thanks to the mode-seeking property of reverse KL. Empirically, our algorithm can outperform existing offline RL algorithms in the MuJoCo locomotion tasks with the standard D4RL datasets as well as the mixed datasets that combine the standard datasets.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

yuanying-cc/td3-rkl officialmentioned in papermentioned on GitHubMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

D4RLMuJoCoOffline RLReinforcement Learning (RL)reinforcement-learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AdamClipped Double Q-learningDense ConnectionsExperience ReplayReLUTD3Target Policy Smoothingfail

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections