ランジェバン誘導フローマッチングによる自動運転向けリアルタイム生成ポリシー
Real-Time Generative Policy via Langevin-Guided Flow Matching for Autonomous Driving
フローマッチングをオンライン強化学習に導入し、ランジェバンダイナミクスで経験を動的に最適化することで、1回の推論で高品質な行動を生成する低遅延な自動運転ポリシーを実現した。
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: Tianze Zhu, Yinuo Wang, Wenjun Zou, Tianyi Zhang, Likun Wang, Letian Tao, Feihong Zhang, Yao Lyu, Shengbo Eben Li
分類: cs.LG, cs.RO
原文アブストラクト
Reinforcement learning (RL) is a fundamental methodology in autonomous driving systems, where generative policies exhibit considerable potential by leveraging their ability to model complex distributions to enhance exploration. However, their inherent high inference latency severely impedes their deployment in real-time decision-making and control. To address this issue, we propose diffusion actor-critic with entropy regulator via flow matching (DACER-F) by introducing flow matching into online RL, enabling the generation of competitive actions in a single inference step. By leveraging Langevin dynamics and gradients of the Q-function, DACER-F dynamically optimizes actions from experience replay toward a target distribution that balances high Q-value information with exploratory behavior. The flow policy is then trained to efficiently learn a mapping from a simple prior distribution to this dynamic target. In complex multi-lane and intersection simulations, DACER-F outperforms baselines diffusion actor-critic with entropy regulator (DACER) and distributional soft actor-critic (DSAC), while maintaining an ultra-low inference latency. DACER-F further demonstrates its scalability on standard RL benchmark DeepMind Control Suite (DMC), achieving a score of 775.8 in the humanoid-stand task and surpassing prior methods. Collectively, these results establish DACER-F as a high-performance and computationally efficient RL algorithm.
