Gaze on the Prize: Shaping Visual Attention with Return-Guided Contrastive Learning
This addresses sample inefficiency for visual RL agents in high-dimensional image tasks, though it is incremental as it builds on existing attention and contrastive learning methods.
The paper tackles the problem of sample inefficiency in visual reinforcement learning by introducing a learnable foveal attention mechanism guided by return differences, achieving up to 2.4x improvement in sample efficiency and solving tasks that baselines fail on in manipulation benchmarks.
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 2.4x improvement in sample efficiency and can solve tasks that the baseline fails to learn, demonstrated across a suite of manipulation tasks from the ManiSkill3 benchmark, all without modifying the underlying algorithm or hyperparameters.