Knowledge Diversion for Efficient Morphology Control and Policy Transfer
School of Computer Science and Engineering, Southeast University, Nanjing, China(计算机科学与工程学院,东南大学,南京,中国);Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, China(新一代人工智能技术及其交叉应用重点实验室(东南大学),教育部,中国)
Universal morphology control aims to learn a universal policy that generalizes across heterogeneous agent morphologies, with Transformer-based controllers emerging as a popular choice. However, such architectures incur substantial computational costs, resulting in high deployment overhead, and existing methods exhibit limited cross-task generalization, necessitating training from scratch for each new task. To this end, we propose \textbf{DivMorph}, a modular training paradigm that leverages knowledge diversion to learn decomposable controllers. DivMorph factorizes randomly initialized Transformer weights into factor units via SVD prior to training and employs dynamic soft gating to modulate these units based on task and morphology embeddings, separating them into shared \textit{learngenes} and morphology- and task-specific \textit{tailors}, thereby achieving knowledge disentanglement. By selectively activating relevant components, DivMorph enables scalable and efficient policy deployment while supporting effective policy transfer to novel tasks. Extensive experiments demonstrate that DivMorph achieves state-of-the-art performance, achieving a 3$\times$ improvement in sample efficiency over direct finetuning for cross-task transfer and a 17$\times$ reduction in model size for single-agent deployment.
Efficient Morphology-Control Co-Design via Stackelberg Proximal Policy Optimization
Center of Excellence for Generative AI, King Abdullah University of Science and Technology (KAUST)(生成人工智能卓越中心,卡奥斯特大学);Dalle Molle Institute for Artificial Intelligence Research (IDSIA)(人工智能研究达勒莫利研究所);Università della Svizzera italiana (USI)(瑞士意大利大学);Scuola universitaria professionale della Svizzera italiana (SUPSI)(瑞士意大利专业大学)
One Policy to Run Them All: an End-to-end Learning Approach to Multi-Embodiment Locomotion
Department of Computer Science, Technical University of Darmstadt(德累斯顿技术大学计算机科学系);Institute of Robotics and Machine Intelligence, Poznan University of Technology(波兹南技术大学机器人与机器智能研究所);German Research Center for AI (DFKI), Research Department: Systems AI for Robot Learning(德国人工智能研究中心(DFKI)系统AI for机器人学习研究部);IDEAS NCBR, Warsaw, Poland(华沙波兰IDEAS NCBR);Centre for Cognitive Science(认知科学中心)
RecMorph: Topology-Guided Spatial Recurrence for Generalized Morphology Control
Jilin University(吉林大学);State Key Laboratory of Special Vehicle Design and Manufacturing Integration Technology(特种车辆设计制造集成技术全国重点实验室);Changchun University of Science and Technology(长春理工大学)
AdaptNet: Policy Adaptation for Physics-Based Character Control
Clemson University(克莱姆森大学);Roblox(Roblox公司);McGill University(麦吉尔大学);École de Technologie Supérieure(蒙特利尔高等技术学院);University of California, Davis(加州大学戴维斯分校);University of Waterloo(滑铁卢大学);University of California, Riverside(加州大学河滨分校)