用注意力机制筛选关键物体，让强化学习更泛化
Deep Reinforcement Learning via Object-Centric Attention
- 通过遮罩机制只关注任务相关的视觉物体
- 在Atari上减少样本需求，对新干扰更鲁棒
- 无需符号表示或特定物体提取，适合通用场景
基于原始像素输入的深度强化学习代理往往无法泛化到训练环境之外，依赖虚假相关性与无关背景。为此，对象中心代理应运而生，但需针对任务设计不同表示。与深度代理不同，单一对象中心架构无法适用于所有环境。受认知科学与奥卡姆剃刀原理启发，我们提出基于遮罩的对象中心注意力（OCCAM），选择性保留任务相关实体，过滤无关视觉信息。具体地，OCCAM利用对象中心归纳偏置。在Atari基准上的实证评估表明，OCCAM显著提升了对新扰动的鲁棒性，降低样本复杂度，且性能与传统像素基强化学习相当或更优。结果表明，结构化抽象可在不依赖显式符号表示或领域特定物体提取流程的情况下增强泛化能力。
原文摘要 · Abstract (English)
Deep reinforcement learning agents, trained on raw pixel inputs, often fail to generalize beyond their training environments, relying on spurious correlations and irrelevant background details. To address this issue, object-centric agents have recently emerged. However, they require different representations tailored to the task specifications. Contrary to deep agents, no single object-centric architecture can be applied to any environment. Inspired by principles of cognitive science and Occam's Razor, we introduce Object-Centric Attention via Masking (OCCAM), which selectively preserves task-relevant entities while filtering out irrelevant visual information. Specifically, OCCAM takes advantage of the object-centric inductive bias. Empirical evaluations on Atari benchmarks demonstrate that OCCAM significantly improves robustness to novel perturbations and reduces sample complexity while showing similar or improved performance compared to conventional pixel-based RL. These results suggest that structured abstraction can enhance generalization without requiring explicit symbolic representations or domain-specific object extraction pipelines.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。