価値条件付き最適化による拡散ポリシーを用いたオフライン強化学習
Diffusion Policies with Value-Conditional Optimization for Offline Reinforcement Learning
オフライン強化学習において、拡散モデルをアドバンテージ値で重み付けして訓練し、高リターン行動を選択的に拡張することで、保守性と探索性のバランスを取る手法DIVOを提案した論文。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Yunchang Ma, Tenglong Liu, Yixing Lan, Xin Yin, Changxin Zhang, Xinglong Zhang, Xin Xu
分類: cs.LG, cs.AI, cs.RO
原文アブストラクト
In offline reinforcement learning, value overestimation caused by out-of-distribution (OOD) actions significantly limits policy performance. Recently, diffusion models have been leveraged for their strong distribution-matching capabilities, enforcing conservatism through behavior policy constraints. However, existing methods often apply indiscriminate regularization to redundant actions in low-quality datasets, resulting in excessive conservatism and an imbalance between the expressiveness and efficiency of diffusion modeling. To address these issues, we propose DIffusion policies with Value-conditional Optimization (DIVO), a novel approach that leverages diffusion models to generate high-quality, broadly covered in-distribution state-action samples while facilitating efficient policy improvement. Specifically, DIVO introduces a binary-weighted mechanism that utilizes the advantage values of actions in the offline dataset to guide diffusion model training. This enables a more precise alignment with the dataset's distribution while selectively expanding the boundaries of high-advantage actions. During policy improvement, DIVO dynamically filters high-return-potential actions from the diffusion model, effectively guiding the learned policy toward better performance. This approach achieves a critical balance between conservatism and explorability in offline RL. We evaluate DIVO on the D4RL benchmark and compare it against state-of-the-art baselines. Empirical results demonstrate that DIVO achieves superior performance, delivering significant improvements in average returns across locomotion tasks and outperforming existing methods in the challenging AntMaze domain, where sparse rewards pose a major difficulty.
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
