FLAG: 潜在拡張ガイダンスによるフローポリシーMaxEnt-RL
FLAG: Flow Policy MaxEnt-RL by Latent Augmented Guidance
最大エントロピー強化学習において、重要度重みの崩壊を避けるためサンプリング領域を局所化し、フロー潜在変数で状態空間を拡張して代理目的を最適化する手法FLAGを提案。高次元制御タスクでSOTA性能を達成。
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: Sungha Kim, Gawon Lee, Jusuk Lee, Jonghae Park, H. Jin Kim, Daesol Cho
分類: cs.LG, cs.RO
原文アブストラクト
Maximum entropy reinforcement learning (MaxEnt-RL) enables robust exploration, yet practical implementations often restrict policies to simple Gaussians. While recent approaches incorporate expressive generative policies via importance-weighted supervised learning, they are prone to importance weight collapse, which limits their scalability in high-dimensional action spaces. Our key insight is to mitigate this limitation by localizing the sampling region, avoiding the weight degeneracy induced by importance sampling over the entire action space. To instantiate this insight, we introduce \textbf{FLAG} (\textbf{F}low policy with \textbf{L}atent-\textbf{A}ugmented \textbf{G}uidance). FLAG augments the state space with a flow latent variable and optimizes a provably consistent proxy MaxEnt-RL objective. We empirically demonstrate that FLAG enables expressive policy optimization with limited importance samples and scales to high-dimensional control tasks. Furthermore, FLAG achieves state-of-the-art performance across challenging benchmarks. Our project webpage: https://flag-rl.github.io/
