arXiv cs.AI· Cedric Derstroff, Jannis Bl\"uml, Janosch Moos, Michael Girstl, Zihan Ye, Debora Clever, Kristian Kersting·· 12 小时前AI 评分31
从绝对到相对表示：ORCA 与 ORBiT 重构以对象为中心的强化学习
Reframing Object-Centric Reinforcement Learning: From Absolute to Relative Representations
AI 导读
研究提出以锚点固定的对象相对坐标 ORCA，并构建基于 Transformer 的 ORBiT 架构处理锚点相对输入。相对表示同时提升了 MLP 与 Transformer 智能体的表现，ORBiT 在 13 款 Atari 游戏上聚合 HNS IQM 超过 1.0，优于基于像素的 PPO 基线，并从零学会 Foosball 游戏、全面压制所有基线。
正文 · 原文
Abstract:Object-centric reinforcement learning agents typically receive each object's position in a fixed global frame, even though their decisions usually depend on where objects are relative to one another. These absolute views often fail to capture the local context that is most relevant to the agent's behavior. As a result, an agent must relearn the same response at every location where a configuration can occur, and its performance collapses when the scene is merely shifted. In this work, we propose a shift toward Object-Relative Coordinates fixed to Anchor (ORCA), where entities are described in a relative frame of reference. To operationalize this idea, we introduce Object-Relative inductive-Bias Transformers (ORBiT), a transformer-based architecture for processing anchor-relative inputs in reinforcement learning. Our results suggest these relative representations improve performance for both MLP and transformer agents. Furthermore, we demonstrate that ORBiT outperforms the pixel-based PPO baseline, achieving an aggregate HNS IQM greater than 1.0 over 13 Atari games. ORBiT learns the game of Foosball from scratch, dominating all baselines. In our controlled Tag environment, we further show that ORCA extends to rotations, that ORBiT generalizes to unseen numbers of distractors, and that these gains require a decision-relevant anchor.
| Comments: | 13 pages, 7 figures, 10 pages Appendix, First two authors contributed equally |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.28197 [cs.LG] |
| (or arXiv:2610.28197v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.28197 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Cedric Derstroff [view email]
[v1]
Tue, 20 Oct 2026 13:38:23 UTC (990 KB)
来源：arXiv cs.AI · arxiv.org