用模块化循环结构让机器人控制器通用化，提升对未知机器人的零样本泛化能力。
Shared Modular Recurrence in Contextual MDPs for Universal Morphology Control
- 基于Transformer设计共享模块化循环架构，利用模块间交互恢复缺失的上下文特征。
- 在四个环境中实现对未见过动力学、运动学和拓扑结构机器人的显著零样本泛化性能提升。
- 适合需要跨形态机器人控制的通用智能体研究者或工业自动化场景应用。
通用机器人控制器能极大提升计算与数据效率。已有研究通过利用个体机器人属性的上下文信息，并利用深度强化学习代理的模块化结构来推进多机器人控制。然而，当机器人形态差异较大时，尤其在需泛化至训练中未见的新机器人时，这一问题变得极具挑战性。本文提出，上下文特征常部分缺失，但可通过模块化交互进行恢复。这有助于实现更优的多机器人控制并提升对未见情境的泛化能力。为此，我们构建了基于Transformer的共享模块化循环架构，并在大量MuJoCo机器人上评估其泛化性能。结果表明，在四种不同环境中，该方法对具有未见动力学、运动学及拓扑结构的机器人均实现了显著的零样本泛化性能提升。
原文摘要 · Abstract (English)
A universal controller for any robot morphology would greatly improve computational and data efficiency. Steps have been made towards such multi-robot control by utilizing contextual information about the properties of individual robots and exploiting their modular structure in the architecture of deep reinforcement learning agents. When the robots have highly dissimilar morphologies, however, this becomes a challenging problem, especially when the agent must generalize to new, unseen robots. In this paper, we posit that contextual features are often only partially available, but that they can be recovered through modular interactions. This can allow for better multi-robot control and generalization to contexts that are not seen during training. To this extent, we implement a transformer-based architecture with shared modular recurrence and evaluate its (generalization) performance on a large set of MuJoCo robots. The results show a substantial improvement in zero-shot generalization performance on robots with unseen dynamics, kinematics, and topologies, in four different environments.
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。