混合データセットからのオフライン強化学習のための逆KL正則化付きTD3
TD3 with Reverse KL Regularizer for Offline Reinforcement Learning from Mixed Datasets
複数の方策から収集した混合データセットを用いるオフライン強化学習において、状態ごとに適応的な重み付けをした逆KLダイバージェンスをBC正則化としてTD3に組み込み、OOD行動の選択を避けつつ性能を向上させる手法を提案。
著者: Yuanying Cai, Chuheng Zhang, Li Zhao, Wei Shen, Xuyun Zhang, Lei Song, Jiang Bian, Tao Qin, Tieyan Liu
分類: stat.ML, cs.AI, cs.LG
原文アブストラクト
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.
関連論文
- FaST: オフライン強化学習のための遷移の因子分解合成オフライン強化学習
- 拡散ポリシーで誘導する拡散プランナーによるオフライン強化学習オフライン強化学習
- MAC-v2: ピクセル入力からの長期的モデルベース価値展開オフライン強化学習
- タスク認識表現を備えたDecision Transformerによるオフライン・メタ強化学習オフライン強化学習
- 効率的な拡散オフライン強化学習のための合成的平均速度モデリングオフライン強化学習
- 対話制約付きオフライン強化学習による自動運転オフライン強化学習
