報酬で視線を導く:リターン誘導コントラスト学習による視覚的注意の形成
Gaze on the Prize: Shaping Visual Attention with Return-Guided Contrastive Learning
人間の中心窩視に着想を得て、リターンの差を自己教師信号として視覚RLエージェントに学習可能な注意機構を組み込み、サンプル効率を最大2.52倍改善した研究。
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: Andrew Lee, Ian Chuang, Dechen Gao, Kai Fukazawa, Iman Soltani
分類: cs.CV, cs.AI, cs.RO
原文アブストラクト
Visual Reinforcement Learning (RL) agents must learn to act based on high-dimensional image data where only a small fraction of the pixels is task-relevant. This forces agents to waste exploration and computational resources on irrelevant features, leading to sample-inefficient and unstable learning. To address this, inspired by human visual foveation, we introduce Gaze on the Prize. This framework augments visual RL with a learnable foveal attention mechanism (Gaze), guided by a self-supervised signal derived from the agent's experience pursuing higher returns (the Prize). Our key insight is that return differences reveal what matters most: If two similar representations produce different outcomes, their distinguishing features are likely task-relevant, and the gaze should focus on them accordingly. This is realized through return-guided contrastive learning that trains the attention to distinguish between the features relevant to success and failure. We group similar visual representations into positives and negatives based on their return differences and use the resulting labels to construct contrastive triplets. These triplets provide the training signal that teaches the attention mechanism to produce distinguishable representations for states associated with different outcomes. Our method achieves up to 2.52x improvement in sample efficiency and can solve challenging tasks from the ManiSkill3 benchmark that the baseline fails to learn, without modifying the underlying algorithm or hyperparameters.
