事前分布マッピング共進化による拡散ポリシーの学習
Training Diffusion Policies via Prior-Mapping Co-Evolution
強化学習において、最適化しやすい潜在空間で方策を訓練しつつ、条件付き生成デコーダで行動を合成するフレームワークGoRLを提案。複雑な連続制御タスクで既存手法を大幅に上回る性能を達成した。
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: Chubin Zhang, Zhenglin Wan, Feng Chen, Fuchao Yang, Lang Feng, Yaxin Zhou, Xingrui Yu, Yang You, Ivor Tsang, Bo An
分類: cs.LG
原文アブストラクト
Reinforcement learning (RL) faces a persistent tension: policies that are stable to optimize (e.g., Gaussians) are often too simple to represent the multimodal action distributions required for complex control. Conversely, expressive generative policies -- such as diffusion and flow matching -- can be difficult to optimize in online RL due to intractable likelihoods and gradients propagating through long sampling chains. We address this tension with a key structural principle: decoupling optimization from generation. Building on this, we introduce GoRL (Generative Online Reinforcement Learning), an algorithm-agnostic framework that trains expressive policies from scratch by confining policy optimization to a tractable latent space while delegating action synthesis to a conditional generative decoder. Viewed as prior-mapping co-evolution, each stage first improves a tractable latent prior through RL and then consolidates the resulting behavior into a more expressive prior-to-action mapping. This two-timescale schedule, anchored by fixed-prior decoder refinement, enables stable optimization while continuously expanding expressiveness. Empirically, \textsc{GoRL} consistently outperforms unimodal and generative baselines across diverse continuous-control tasks. Notably, GoRL achieves returns exceeding 870 on HopperStand, more than 3* the strongest baseline; on high-dimensional humanoid tasks, it further outperforms the strongest non-GoRL baseline by over an order of magnitude.
関連論文
- ReFPO: フローマッチングポリシー勾配のためのリフロー正則化強化学習/生成ポリシー
