学习控制自组装形态:基于模块化的泛化研究
Learning to Control Self-Assembling Morphologies: A Study of Generalization via Modularity
摘要:
当代感觉运动学习方法通常从现有的复杂代理(例如,机器人手臂),他们学会控制。相比之下,本文研究了一个模块化的共同演化策略:一个原始代理的集合学习动态自组装成复合体,同时也学习协调他们的行为来控制这些机构。每一个原始智能体都由一个肢体组成,肢体的一端连接着一个马达。肢体可以选择连接起来形成集体。当一个肢体发起连接动作,并且附近有另一个肢体时,后者被磁性连接到“父”肢体的电机。这就形成了一个新的单一代理人,它可以进一步与其他代理人联系起来。通过这种方式,可以出现复杂的形态,由其架构与形态显式对应的策略控制。我们评估这些动态和模块化的代理在模拟环境中的性能。我们展示了更好的泛化测试时的变化,无论是在环境中,以及在代理的结构,相比静态和单片基线。项目视频和代码可在https://pathak22.github.io/modular-assemblies/上获得
英文摘要:
Contemporary sensorimotor learning approaches typically start with an existing complex agent (e.g., a robotic arm), which they learn to control. In contrast, this paper investigates a modular co-evolution strategy: a collection of primitive agents learns to dynamically self-assemble into composite bodies while also learning to coordinate their behavior to control these bodies. Each primitive agent consists of a limb with a motor attached at one end. Limbs may choose to link up to form collectives. When a limb initiates a link-up action, and there is another limb nearby, the latter is magnetically connected to the 'parent' limb's motor. This forms a new single agent, which may further link with other agents. In this way, complex morphologies can emerge, controlled by a policy whose architecture is in explicit correspondence with the morphology. We evaluate the performance of these dynamic and modular agents in simulated environments. We demonstrate better generalization to test-time changes both in the environment, as well as in the structure of the agent, compared to static and monolithic baselines. Project video and code are available at https://pathak22.github.io/modular-assemblies/
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。