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，一个用于物理模拟人形角色灵活运动适应的框架。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和正则化项，训练掩码不变基策略，该正则化项强制不同掩码条件下的动作分布保持一致，从而生成鲁棒的运动先验，能在观测缺失时保持稳定，并预测后续对相应区域的适应。第二阶段，在冻结的基控制器上训练残差策略，仅修改目标身体部位的行为，同时保留其他区域的原始运动。通过两个应用实例展示该设计的通用性：（i）运动组合，其中不同掩码可对同一序列中的多部位进行适应；（ii）文本驱动局部目标追踪，指定身体部位跟随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具备强鲁棒性与适应性，在掩码观测下生成多样化行为，并在目标运动适应方面优于先前方法。