# ForgetMimic: Motion Unlearning for Reinforcement Learning Humanoid Control

arXiv: https://arxiv.org/abs/2609.28378 · HTML: https://mlsanity.com/paper/2609.28378/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Machine unlearning, one of 12 directions in LLM safety and security.
- Builds on 33 of its 41 references that are in the map.
- First posted on arXiv 23 Sep 2026.

## Placed in

- LLM safety and security / [Machine unlearning](https://mlsanity.com/safety/machine-unlearning/)
- Deep reinforcement learning methods / [RL for robot locomotion and manipulation](https://mlsanity.com/deeprl/rl-for-robot-locomotion-and-manipulation/)

## Builds on (most cited first, 30 of 33)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [High-Dimensional Continuous Control Using Generalized Advantage Estimation](https://mlsanity.com/paper/1506.02438/) (2015)
- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learning](https://mlsanity.com/paper/2109.11978/) (2021)
- [Making AI Forget You: Data Deletion in Machine Learning](https://mlsanity.com/paper/1907.05012/) (2019)
- [Remember What You Want to Forget: Algorithms for Machine Unlearning](https://mlsanity.com/paper/2103.03279/) (2021)
- [Robust Motion In-betweening](https://mlsanity.com/paper/2102.04942/) (2021)
- [When Machine Unlearning Jeopardizes Privacy](https://mlsanity.com/paper/2005.02205/) (2020)
- [BeyondMimic: From Motion Tracking to Versatile Humanoid Control via Guided Diffusion](https://mlsanity.com/paper/2508.08241/) (2025)
- [World-Grounded Human Motion Recovery via Gravity-View Coordinates](https://mlsanity.com/paper/2409.06662/) (2024)
- [Machine Unlearning for Random Forests](https://mlsanity.com/paper/2009.05567/) (2020)
- [Universal Humanoid Motion Representations for Physics-Based Control](https://mlsanity.com/paper/2310.04582/) (2023)
- [MaskedMimic: Unified Physics-Based Character Control Through Masked Motion Inpainting](https://mlsanity.com/paper/2409.14393/) (2024)
- [TWIST: Teleoperated Whole-Body Imitation System](https://mlsanity.com/paper/2505.02833/) (2025)
- [SONIC: Supersizing Motion Tracking for Natural Humanoid Whole-Body Control](https://mlsanity.com/paper/2511.07820/) (2025)
- [Humanoid Locomotion and Manipulation: Current Progress and Challenges in Control, Planning, and Learning](https://mlsanity.com/paper/2501.02116/) (2025)
- [Private Reinforcement Learning with PAC and Regret Guarantees](https://mlsanity.com/paper/2009.09052/) (2020)
- [mjlab: A Lightweight Framework for GPU-Accelerated Robot Learning](https://mlsanity.com/paper/2601.22074/) (2026)
- [Differentially Private Reinforcement Learning with Linear Function Approximation](https://mlsanity.com/paper/2201.07052/) (2022)
- [Reinforcement Unlearning](https://mlsanity.com/paper/2312.15910/) (2023)
- [Near-Optimal Differentially Private Reinforcement Learning](https://mlsanity.com/paper/2212.04680/) (2022)
- [Near-Optimal Randomized Exploration for Tabular Markov Decision Processes](https://mlsanity.com/paper/2102.09703/) (2021)
- [EEPO: Exploration-Enhanced Policy Optimization via Sample-Then-Forget](https://mlsanity.com/paper/2510.05837/) (2025)
- [OmniXtreme: Breaking the Generality Barrier in High-Dynamic Humanoid Control](https://mlsanity.com/paper/2602.23843/) (2026)
- [ZEST: Zero-shot Embodied Skill Transfer for Athletic Robot Control](https://mlsanity.com/paper/2602.00401/) (2026)
- [Sharpness-Aware Machine Unlearning](https://mlsanity.com/paper/2506.13715/) (2025)
- [TrajDeleter: Enabling Trajectory Forgetting in Offline Reinforcement Learning Agents](https://mlsanity.com/paper/2404.12530/) (2024)
- [Attention Smoothing Is All You Need For Unlearning](https://mlsanity.com/paper/2603.01285/) (2026)
- [Gaussian Certified Unlearning in High Dimensions: A Hypothesis Testing Approach](https://mlsanity.com/paper/2510.13094/) (2025)
- [VLALeaks: Membership Inference Attacks against Vision-Language-Action Models](https://mlsanity.com/paper/2606.15165/) (2026)

## Abstract (arXiv)

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 πθ 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.