ForgetMimic：让人形机器人定向遗忘特定动作的强化学习方法
ForgetMimic: Motion Unlearning for Reinforcement Learning Humanoid Control
给机器人策略做"删除指定动作"的遗忘方法，在 Unitree G1 和 H2 上验证过，涉及 GDPR 和安全问题的话很值得看看思路。
arXiv 论文提出 ForgetMimic，这是首个面向物理世界人形机器人控制的动作级遗忘方法。该方法针对在 N 个动作上训练的策略 π_θ，只降低其中 K 个目标动作的性能，同时保留其余 N-K 个动作的效果。研究动机包括清除恶意或投毒动作，以及满足 GDPR 被遗忘权下版权动作的删除要求。实验覆盖 Unitree G1 和 H2 两款人形机器人的 12 个动作，包括 Dance、Fight、Flip 等，结果显示目标动作被有效遗忘且其余动作正常运行。
ForgetMimic: Motion Unlearning for Reinforcement Learning Humanoid Control
Humanoid control, leveraging human demonstrations, has achieved diverse, agile, and natural locomotion behaviors through reinforcement learning (RL). While this paradigm has yielded remarkable performance in physical humanoid control, how to eliminate specific motions from learned policies remains insufficiently explored. Addressing this issue is motivated by pressing safety and privacy concerns: the removal of malicious, poisoned, or suboptimal motions, as well as copyright-protected motions subject to the right to be forgotten under regulations such as the GDPR, is of critical importance. To this end, we propose {ForgetMimic}, the first motion-level unlearning method designed specifically for physical-world humanoid control. The core idea of ForgetMimic is as follows: given a policy $π_θ$ trained on $N$ motions, our method degrades performance on a target subset of $K$ motions while preserving the effectiveness of the remaining $N-K$ motions. Furthermore, we identify and resolve two key training mechanisms in robot control that lead to unlearning failure. We conduct extensive experiments on the Unitree G1 and H2 humanoid robots across 12 motions, including Dance, Fight, Flip, and others. Experimental results demonstrate that ForgetMimic effectively eliminates memory of designated motions while maintaining the normal operation of all other motions.
