TeViR: 拡散モデルによるテキストから動画への報酬生成で効率的な強化学習
TeViR: Text-to-Video Reward with Diffusion Models for Efficient Reinforcement Learning
テキストから動画を生成する拡散モデルを使い、予測映像と現在の観測を比較して密な報酬を生成する強化学習手法を提案。11の複雑なロボット操作タスクでサンプル効率と性能を向上させた。
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: Yuhui Chen, Haoran Li, Zhennan Jiang, Haowei Wen, Dongbin Zhao
分類: cs.RO, cs.AI
原文アブストラクト
Developing scalable and generalizable reward engineering for reinforcement learning (RL) is crucial for creating general-purpose agents, especially in the challenging domain of robotic manipulation. While recent advances in reward engineering with Vision-Language Models (VLMs) have shown promise, their sparse reward nature significantly limits sample efficiency. This paper introduces TeViR, a novel method that leverages a pre-trained text-to-video diffusion model to generate dense rewards by comparing the predicted image sequence with current observations. Experimental results across 11 complex robotic tasks demonstrate that TeViR outperforms traditional methods leveraging sparse rewards and other state-of-the-art (SOTA) methods, achieving better sample efficiency and performance without ground truth environmental rewards. TeViR's ability to efficiently guide agents in complex environments highlights its potential to advance reinforcement learning applications in robotic manipulation.
