We present MaskAdapt, a framework for flexible motion adaptation in physics-based humanoid control. The framework follows a two-stage residual learning paradigm. In the first stage, we train a mask-invariant base policy using stochastic body-part masking and a regularization term that enforces consistent action distributions across masking conditions. This yields a robust motion prior that remains stable under missing observations, anticipating later adaptation in those regions. In the second stage, a residual policy is trained atop the frozen base controller to modify only the targeted body parts while preserving the original behaviors elsewhere. We demonstrate the versatility of this design through two applications: (i) motion composition, where varying masks enable multi-part adaptation within a single sequence, and (ii) text-driven partial goal tracking, where designated body parts follow kinematic targets provided by a pre-trained text-conditioned autoregressive motion generator. Through experiments, MaskAdapt demonstrates strong robustness and adaptability, producing diverse behaviors under masked observations and delivering superior targeted motion adaptation compared to prior work.

翻译：摘要：我们提出MaskAdapt——一个面向物理仿真类人控制的灵活运动自适应框架。该框架采用两阶段残差学习范式：第一阶段通过随机身体部位掩码与正则化项训练掩码不变基策略，其中正则化项强制不同掩码条件间的动作分布一致性，从而获得对缺失观测具有鲁棒性的运动先验，并为后续局部区域自适应预留空间；第二阶段在冻结的基控制器上层训练残差策略，仅修改目标身体部位，同时保持其他区域原始行为。通过两项应用验证该设计的通用性：（i）运动合成——通过可变掩码实现单序列内多部位自适应；（ii）文本驱动的局部目标追踪——指定身体部位遵循预训练文本条件自回归运动生成器提供的运动学目标。实验表明，MaskAdapt在掩码观测条件下展现出强鲁棒性与适应能力，相比现有方法能生成多样化行为并实现更优的定向运动自适应。