ADD: Physics-Based Motion Imitation with Adversarial Differential Discriminators

• URL: http://arxiv.org/abs/2505.04961v1
• Date: Thu, 08 May 2025 05:42:33 GMT
• Title: ADD: Physics-Based Motion Imitation with Adversarial Differential Discriminators
• Authors: Ziyu Zhang, Sergey Bashkirov, Dun Yang, Michael Taylor, Xue Bin Peng,
• Abstract summary: We present a novel adversarial multi-objective optimization technique that is broadly applicable to a range of multi-objective optimization problems, including motion tracking.<n>We demonstrate that our technique can enable characters to replicate a variety of acrobatic and agile behaviors, achieving comparable quality to state-of-the-art motion-tracking methods.
• Score: 9.410279213317649
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Multi-objective optimization problems, which require the simultaneous optimization of multiple terms, are prevalent across numerous applications. Existing multi-objective optimization methods often rely on manually tuned aggregation functions to formulate a joint optimization target. 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 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 adjustment, 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 optimization problems, including motion tracking. The proposed adversarial differential discriminator 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 tuned reward functions. Results are best visualized through https://youtu.be/rz8BYCE9E2w.

Related papers

• Continual Optimization with Symmetry Teleportation for Multi-Task Learning [73.28772872740744]
  Multi-task learning (MTL) enables the simultaneous learning of multiple tasks using a single model.<n>We propose a novel approach based on Continual Optimization with Symmetry Teleportation (COST)<n>COST seeks an alternative loss-equivalent point on the loss landscape to reduce conflict gradients.
  arXiv  Detail & Related papers  (2025-03-06T02:58:09Z)
• Unlearning as multi-task optimization: A normalized gradient difference approach with an adaptive learning rate [105.86576388991713]
  We introduce a normalized gradient difference (NGDiff) algorithm, enabling us to have better control over the trade-off between the objectives.<n>We provide a theoretical analysis and empirically demonstrate the superior performance of NGDiff among state-of-the-art unlearning methods on the TOFU and MUSE datasets.
  arXiv  Detail & Related papers  (2024-10-29T14:41:44Z)
• M$^2$PT: Multimodal Prompt Tuning for Zero-shot Instruction Learning [90.75075886543404]
  Multimodal Large Language Models (MLLMs) demonstrate remarkable performance across a wide range of domains. In this work, we introduce a novel Multimodal Prompt Tuning (M$2$PT) approach for efficient instruction tuning of MLLMs.
  arXiv  Detail & Related papers  (2024-09-24T01:40:24Z)
• End-to-End Learning for Fair Multiobjective Optimization Under Uncertainty [55.04219793298687]
  The Predict-Then-Forecast (PtO) paradigm in machine learning aims to maximize downstream decision quality. This paper extends the PtO methodology to optimization problems with nondifferentiable Ordered Weighted Averaging (OWA) objectives. It shows how optimization of OWA functions can be effectively integrated with parametric prediction for fair and robust optimization under uncertainty.
  arXiv  Detail & Related papers  (2024-02-12T16:33:35Z)
• Deep-ELA: Deep Exploratory Landscape Analysis with Self-Supervised Pretrained Transformers for Single- and Multi-Objective Continuous Optimization Problems [0.5461938536945723]
  In this work, we propose a hybrid approach, Deep-ELA, which combines (the benefits of) deep learning and ELA features. Our proposed framework can either be used out-of-the-box for analyzing single- and multi-objective continuous optimization problems, or subsequently fine-tuned to various tasks.
  arXiv  Detail & Related papers  (2024-01-02T12:41:17Z)
• DiffVL: Scaling Up Soft Body Manipulation using Vision-Language Driven Differentiable Physics [69.6158232150048]
  DiffVL is a method that enables non-expert users to communicate soft-body manipulation tasks. We leverage large language models to translate task descriptions into machine-interpretable optimization objectives.
  arXiv  Detail & Related papers  (2023-12-11T14:29:25Z)
• An Empirical Evaluation of Zeroth-Order Optimization Methods on AI-driven Molecule Optimization [78.36413169647408]
  We study the effectiveness of various ZO optimization methods for optimizing molecular objectives. We show the advantages of ZO sign-based gradient descent (ZO-signGD) We demonstrate the potential effectiveness of ZO optimization methods on widely used benchmark tasks from the Guacamol suite.
  arXiv  Detail & Related papers  (2022-10-27T01:58:10Z)
• Mitigating Gradient Bias in Multi-objective Learning: A Provably Convergent Stochastic Approach [38.76462300149459]
  We develop a Multi-objective Correction (MoCo) method for multi-objective gradient optimization. The unique feature of our method is that it can guarantee convergence without increasing the non fairness gradient.
  arXiv  Detail & Related papers  (2022-10-23T05:54:26Z)
• SE(3)-DiffusionFields: Learning smooth cost functions for joint grasp and motion optimization through diffusion [34.25379651790627]
  This work introduces a method for learning data-driven SE(3) cost functions as diffusion models. We focus on learning SE(3) diffusion models for 6DoF grasping, giving rise to a novel framework for joint grasp and motion optimization.
  arXiv  Detail & Related papers  (2022-09-08T14:50:23Z)
• Multi-Objective Hyperparameter Optimization in Machine Learning -- An Overview [10.081056751778712]
  We introduce the basics of multi-objective hyperparameter optimization and motivate its usefulness in applied ML. We provide an extensive survey of existing optimization strategies, both from the domain of evolutionary algorithms and Bayesian optimization. We illustrate the utility of MOO in several specific ML applications, considering objectives such as operating conditions, prediction time, sparseness, fairness, interpretability and robustness.
  arXiv  Detail & Related papers  (2022-06-15T10:23:19Z)
• Leveraging Trust for Joint Multi-Objective and Multi-Fidelity Optimization [0.0]
  This paper investigates a novel approach to Bayesian multi-objective and multi-fidelity (MOMF) optimization. We suggest the innovative use of a trust metric to support simultaneous optimization of multiple objectives and data sources. Our methods offer broad applicability in solving simulation problems in fields such as plasma physics and fluid dynamics.
  arXiv  Detail & Related papers  (2021-12-27T20:55:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.