arXiv：cs.LG· Aviraj Newatia, Yordan Tsvetkov, Leonard Pleiss, Andrew Spielberg, Rika Antonova·· 3 小时前AI 评分40
Co-design Gym：面向具身与策略协同优化的统一基准
Co-design Gym: A Unified Benchmark for Embodiment-Policy Co-optimization
AI 导读
研究者推出 Co-design Gym，一套用于联合优化具身设计与控制策略的基准环境套件，覆盖机器人操作与运动、多机器人协作、软体动力学、视频游戏、电网、无线网络、F1 赛车、多智能体仓库和最优控制等领域，共 20 个环境族、超过 85 个协同设计预设。该工作还对代表性协同设计算法进行了系统评估，刻画了当前技术水平。
正文
Abstract:Finding an optimal behaviour policy within a given environment is a widely studied problem in domains as diverse as games, robotics, energy infrastructure, communication networks, and multi-agent systems. Numerous benchmarks have been developed to support such research, but the vast majority assume that the agent's embodiment (design) is fixed, focusing instead on policy learning alone. Lifting this assumption gives rise to a broader class of problems in which optimizing embodiment and policy separately is highly suboptimal. An agent's embodiment strongly shapes which control policies can be discovered, while the optimal embodiment is in turn defined by the policies it admits. To help the research community study this class of problems explicitly and systematically, we introduce Co-Design Gym - a suite of benchmark environments for jointly optimizing embodiment and policy. Our environments span domains such as robotic manipulation and locomotion, multi-robot cooperation, deformable and soft dynamics, video games, electricity grids, wireless networks, F1 racing, multi-agent warehouses, and optimal control, offering 20 environment families (domains), with over 85 distinct co-design presets in total. We further contribute a systematic evaluation of representative co-design algorithms, characterizing the current state of the art. Together, these contributions lay the groundwork for cumulative, comparable progress in co-design.
| Comments: | Aviraj Newatia and Yordan Tsvetkov contributed equally |
| Subjects: | Machine Learning (cs.LG); Robotics (cs.RO) |
| Cite as: | arXiv:2610.02366 [cs.LG] |
| (or arXiv:2610.02366v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.02366 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Rika Antonova [view email]
[v1]
Thu, 1 Oct 2026 18:42:56 UTC (12,703 KB)
来源：arXiv：cs.LG · arxiv.org