# Physics-Based Motion Imitation with Adversarial Differential Discriminators

arXiv: https://arxiv.org/abs/2505.04961 · HTML: https://mlsanity.com/paper/2505.04961/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 65 references that are in the map.
- First posted on arXiv 8 May 2025.

## Builds on (most cited first, 24 of 24)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [High-Dimensional Continuous Control Using Generalized Advantage Estimation](https://mlsanity.com/paper/1506.02438/) (2015)
- [Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1606.03476/) (2016)
- [Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics](https://mlsanity.com/paper/1705.07115/) (2017)
- [Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning](https://mlsanity.com/paper/2108.10470/) (2021)
- [Which Training Methods for GANs do actually Converge?](https://mlsanity.com/paper/1801.04406/) (2018)
- [End-to-End Multi-Task Learning with Attention](https://mlsanity.com/paper/1803.10704/) (2018)
- [f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization](https://mlsanity.com/paper/1606.00709/) (2016)
- [Robust Motion In-betweening](https://mlsanity.com/paper/2102.04942/) (2021)
- [Perpetual Humanoid Control for Real-time Simulated Avatars](https://mlsanity.com/paper/2305.06456/) (2023)
- [DeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skills](https://mlsanity.com/paper/1804.02717/) (2018)
- [Imitation Learning as f-Divergence Minimization](https://mlsanity.com/paper/1905.12888/) (2019)
- [MaskedMimic: Unified Physics-Based Character Control Through Masked Motion Inpainting](https://mlsanity.com/paper/2409.14393/) (2024)
- [MoConVQ: Unified Physics-Based Motion Control via Scalable Discrete Representations](https://mlsanity.com/paper/2310.10198/) (2023)
- [A Distributional View on Multi-Objective Policy Optimization](https://mlsanity.com/paper/2005.07513/) (2020)
- [UniCon: Universal Neural Controller For Physics-based Character Motion](https://mlsanity.com/paper/2011.15119/) (2020)
- [Meta-Learning for Multi-objective Reinforcement Learning](https://mlsanity.com/paper/1811.03376/) (2018)
- [Composite Motion Learning with Task Control](https://mlsanity.com/paper/2305.03286/) (2023)
- [Animating Human Athletics](https://mlsanity.com/paper/2302.06108/) (2023)
- [A GAN-Like Approach for Physics-Based Imitation Learning and Interactive Character Control](https://mlsanity.com/paper/2105.10066/) (2021)
- [Learning and Exploring Motor Skills with Spacetime Bounds](https://mlsanity.com/paper/2103.16807/) (2021)
- [GROVE: A Generalized Reward for Learning Open-Vocabulary Physical Skill](https://mlsanity.com/paper/2504.04191/) (2025)
- [Learning Bipedal Robot Locomotion from Human Movement](https://mlsanity.com/paper/2105.12277/) (2021)

## Built on by (most cited first, 12 of 12)

- [Heracles: Bridging Precise Tracking and Generative Synthesis for General Humanoid Control](https://mlsanity.com/paper/2603.27756/) (2026)
- [GPC: Large-Scale Generative Pretraining for Transferable Motor Control](https://mlsanity.com/paper/2606.29148/) (2026)
- [PDF-HR: Pose Distance Fields for Humanoid Robots](https://mlsanity.com/paper/2602.04851/) (2026)
- [Scaling Whole-Body Human Musculoskeletal Behavior Emulation for Specificity and Diversity](https://mlsanity.com/paper/2603.29332/) (2026)
- [Stability-Driven Motion Generation for Object-Guided Human-Human Co-Manipulation](https://mlsanity.com/paper/2604.20336/) (2026)
- [DeVI: Physics-based Dexterous Human-Object Interaction via Synthetic Video Imitation](https://mlsanity.com/paper/2604.20841/) (2026)
- [HumanTracker: Towards Comprehensive and Human-Aligned Motion Tracking Benchmark](https://mlsanity.com/paper/2608.13555/) (2026)
- [Neural Assistive Impulses: Synthesizing Exaggerated Motions for Physics-based Characters](https://mlsanity.com/paper/2604.05394/) (2026)
- [FatigueFusion: Latent Space Fusion for Fatigue-Driven Motion Synthesis](https://mlsanity.com/paper/2604.10199/) (2026)
- [SWIM: Compact Environment Representation for Reinforcement Learning Human Swimming](https://mlsanity.com/paper/2605.31120/) (2026)
- [PFM-HR: Pose Flow Matching for Humanoid Robots](https://mlsanity.com/paper/2608.03227/) (2026)
- [Scalable Multi-Human Cooperative Manipulation via Commander-Executor Coordination](https://mlsanity.com/paper/2610.14911/) (2026)

## Abstract (arXiv)

Multi-objective optimization problems, which require the simultaneous optimization of multiple objectives, are prevalent across numerous applications. Existing multi-objective optimization methods often rely on manually-tuned aggregation functions to formulate a joint optimization objective. The performance of such hand-tuned methods is heavily dependent on careful weight selection, a time-consuming and laborious process. These limitations also arise in the setting of reinforcement-learning-based motion tracking methods for physically simulated characters, where intricately crafted reward functions are typically used to achieve high-fidelity results. Such solutions not only require domain expertise and significant manual tuning, but also limit the applicability of the resulting reward function across diverse skills. To bridge this gap, we present a novel adversarial multi-objective optimization technique that is broadly applicable to a range of multi-objective reinforcement-learning tasks, including motion tracking. Our proposed Adversarial Differential Discriminator (ADD) receives a single positive sample, yet is still effective at guiding the optimization process. We demonstrate that our technique can enable characters to closely replicate a variety of acrobatic and agile behaviors, achieving comparable quality to state-of-the-art motion-tracking methods, without relying on manually-designed reward functions. Code and results are available at https://add-moo.github.io/.