DMAP：一种用于学习随身体变化运动的分布式形态注意力策略
DMAP: a Distributed Morphological Attention Policy for Learning to Locomote with a Changing Body
AI总结：
针对身体形态变化下的运动学习难题，提出受生物启发的分布式形态注意力策略DMAP，结合独立本体处理、分布式关节控制器与注意力机制，在无隐藏形态信息的情况下端到端训练，性能达到或超越预言机智能体。
摘要：
生物智能体和人工智能体都需要应对现实世界中的持续变化。我们在四个添加了形态扰动的经典连续控制环境中研究这一问题。当身体不同部位的长度和粗细发生变化时，学习运动是一项具有挑战性的任务，因为控制策略需要适应身体形态，才能成功地让智能体保持平衡并前进。我们发现，基于本体感觉状态的控制策略在身体构型高度可变的情况下表现不佳，而能够获取扰动习得编码的（预言机）智能体表现则显著更优。我们提出了DMAP，一种受生物启发、基于注意力的策略网络架构。DMAP结合了独立的本体感觉处理、为每个关节配备独立控制器的分布式策略，以及一种注意力机制，用于动态调控从不同身体部位流向不同控制器的感官信息。尽管无法获取（隐藏的）形态信息，DMAP仍能在所有研究的环境中进行端到端训练，整体性能达到或超过预言机智能体的水平。因此，DMAP践行了生物运动控制的原理，为学习具有挑战性的感觉运动任务提供了强大的归纳偏置。总的来说，我们的研究证实了这些原理在具有挑战性的运动任务中的效力。
英文摘要：
Biological and artificial agents need to deal with constant changes in the real world. We study this problem in four classical continuous control environments, augmented with morphological perturbations. Learning to locomote when the length and the thickness of different body parts vary is challenging, as the control policy is required to adapt to the morphology to successfully balance and advance the agent. We show that a control policy based on the proprioceptive state performs poorly with highly variable body configurations, while an (oracle) agent with access to a learned encoding of the perturbation performs significantly better. We introduce DMAP, a biologically-inspired, attention-based policy network architecture. DMAP combines independent proprioceptive processing, a distributed policy with individual controllers for each joint, and an attention mechanism, to dynamically gate sensory information from different body parts to different controllers. Despite not having access to the (hidden) morphology information, DMAP can be trained end-to-end in all the considered environments, overall matching or surpassing the performance of an oracle agent. Thus DMAP, implementing principles from biological motor control, provides a strong inductive bias for learning challenging sensorimotor tasks. Overall, our work corroborates the power of these principles in challenging locomotion tasks.
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。
