InstantMimic: A High Performance System for Learning Physics-based Skills in Seconds

• URL: http://arxiv.org/abs/2609.09821v1
• Date: Wed, 09 Sep 2026 07:23:51 GMT
• Title: InstantMimic: A High Performance System for Learning Physics-based Skills in Seconds
• Abstract summary: We present InstantMimic, a system that makes the entire training loop GPU-native.<n>Our unified pipeline integrates simulation, environment, policy inference, and policy updates within a single execution flow.<n>As a result, InstantMimic reduces training time for diverse physics-based skills to a few seconds.
• Score: 4.282159812965446
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Physics-based character control is a long-standing challenge in computer graphics and robotics, requiring policies that satisfy complex dynamics while producing realistic motion. Recent Deep RL approaches, particularly imitation learning methods such as DeepMimic, have had broad impact beyond animation, influencing robotics by enabling agile and expressive behaviors. While these approaches achieve impressive results, they remain computationally inefficient to train in practice. Despite GPU-accelerated simulation, we find that end-to-end pipelines often underutilize hardware due to overheads outside the physics solver, caused by fragmented GPU kernels and CPU memory access in the critical path. We present InstantMimic, a system that addresses these inefficiencies by making the entire training loop GPU-native. Built on a GPU-native physics backend, our unified pipeline integrates simulation, environment computation, policy inference, and policy updates within a single execution flow. As a result, InstantMimic reduces training time for diverse physics-based skills to a few seconds and makes LLM-agent-driven hyperparameter search practical.

Related papers

• UniLab: A Heterogeneous Architecture for Robot RL Beyond GPU-Dominant Paradigms [68.40808444348735]
  In simulation-dominated robot control, the essential question is not which processor runs physics, but whether simulation throughput, policy learning, and runtime synchronization form an efficient end-to-end loop.<n>We present UniLab, a heterogeneous CPU-resident / GPU-learning architecture that decouples CPU-parallel simulation from GPU policy updates through a unified runtime for data movement, buffering, and synchronization.
  arXiv  Detail & Related papers  (2026-05-28T17:53:50Z)
• GS-Playground: A High-Throughput Photorealistic Simulator for Vision-Informed Robot Learning [55.272458304179025]
  GS-Playground is a multi-modal simulation framework designed to accelerate end-to-end perceptual learning.<n>Our system achieves a breakthrough throughput of 104 FPS at 640x480 resolution, significantly lowering the barrier for large-scale visual RL.
  arXiv  Detail & Related papers  (2026-04-28T10:05:39Z)
• SIMPACT: Simulation-Enabled Action Planning using Vision-Language Models [60.80050275581661]
  Vision-Language Models (VLMs) exhibit remarkable common-sense and semantic reasoning capabilities.<n>They lack a grounded understanding of physical dynamics.<n>We present S, a test-time, SIMulation-enabled ACTion Planning framework.<n>Our method demonstrates state-of-the-art performance on five challenging, real-world rigid-body and deformable manipulation tasks.
  arXiv  Detail & Related papers  (2025-12-05T18:51:03Z)
• Hybrid Neural-MPM for Interactive Fluid Simulations in Real-Time [57.30651532625017]
  We present a novel hybrid method that integrates numerical simulation, neural physics, and generative control.<n>Our system demonstrates robust performance across diverse 2D/3D scenarios, material types, and obstacle interactions.<n>We promise to release both models and data upon acceptance.
  arXiv  Detail & Related papers  (2025-05-25T01:27:18Z)
• NeoPhysIx: An Ultra Fast 3D Physical Simulator as Development Tool for AI Algorithms [0.0]
  Traditional AI algorithms, such as Genetic Programming and Reinforcement Learning, often require extensive computational resources to simulate real-world physical scenarios effectively. This paper introduces NeoPhysIx, a novel 3D physical simulator designed to overcome these challenges. By adopting innovative simulation paradigms and focusing on essential algorithmic elements, NeoPhysIx achieves unprecedented speedups exceeding 1000x compared to real-time.
  arXiv  Detail & Related papers  (2024-10-26T09:53:07Z)
• PlasticineLab: A Soft-Body Manipulation Benchmark with Differentiable Physics [89.81550748680245]
  We introduce a new differentiable physics benchmark called PasticineLab. In each task, the agent uses manipulators to deform the plasticine into the desired configuration. We evaluate several existing reinforcement learning (RL) methods and gradient-based methods on this benchmark.
  arXiv  Detail & Related papers  (2021-04-07T17:59:23Z)
• Machine learning accelerated computational fluid dynamics [9.077691121640333]
  We use end-to-end deep learning to improve approximations inside computational fluid dynamics for modeling two-dimensional turbulent flows. For both direct numerical simulation of turbulence and large eddy simulation, our results are as accurate as baseline solvers with 8-10x finer resolution in each spatial dimension. Our approach exemplifies how scientific computing can leverage machine learning and hardware accelerators to improve simulations without sacrificing accuracy or generalization.
  arXiv  Detail & Related papers  (2021-01-28T19:10:00Z)
• Data-Efficient Learning for Complex and Real-Time Physical Problem Solving using Augmented Simulation [49.631034790080406]
  We present a task for navigating a marble to the center of a circular maze. We present a model that learns to move a marble in the complex environment within minutes of interacting with the real system.
  arXiv  Detail & Related papers  (2020-11-14T02:03:08Z)

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.