mlsanityData to 7 Oct 2026

GPU-Accelerated Robotic Simulation for Distributed Reinforcement Learning

arXiv 1810.05762 ↗First posted 12 Oct 2018cs.ROcited by 77

Not on the map. Why?

Abstract (arXiv)

Most Deep Reinforcement Learning (Deep RL) algorithms require a prohibitively large number of training samples for learning complex tasks. Many recent works on speeding up Deep RL have focused on distributed training and simulation. While distributed training is often done on the GPU, simulation is not. In this work, we propose using GPU-accelerated RL simulations as an alternative to CPU ones. Using NVIDIA Flex, a GPU-based physics engine, we show promising speed-ups of learning various continuous-control, locomotion tasks. With one GPU and CPU core, we are able to train the Humanoid running task in less than 20 minutes, using 10-1000x fewer CPU cores than previous works. We also demonstrate the scalability of our simulator to multi-GPU settings to train more challenging locomotion tasks.

Key facts. Cited by 77 papers in the map (data through 7 Oct 2026). First posted on arXiv 12 Oct 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 8; 2022: 12; 2023: 10; 2024: 13; 2025: 23; 2026: 11.

77 papers.

Sort:

By area:

  1. 2021Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learningcited by 882
  2. 2021Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learningcited by 395
  3. 2024VideoPhy: Evaluating Physical Commonsense for Video Generationcited by 215
  4. 2022DexGraspNet: A Large-Scale Robotic Dexterous Grasp Dataset for General Objects Based on Simulationcited by 129
  5. 2025GraspVLA: a Grasping Foundation Model Pre-trained on Billion-scale Synthetic Action Datacited by 120
  6. 2022Accelerated Policy Learning with Parallel Differentiable Simulationcited by 92
  7. 2022Adversarial Motion Priors Make Good Substitutes for Complex Reward Functionscited by 68
  8. 2021Transferring Dexterous Manipulation from GPU Simulation to a Remote Real-World TriFingercited by 34
  9. 2023QuestEnvSim: Environment-Aware Simulated Motion Tracking from Sparse Sensorscited by 26
  10. 2025UniPhys: Unified Planner and Controller with Diffusion for Flexible Physics-Based Character Controlcited by 24
  11. 2025The Reality Gap in Robotics: Challenges, Solutions, and Best Practicescited by 22
  12. 2022Blocks Assemble! Learning to Assemble with Large-Scale Structured Reinforcement Learningcited by 21
38 more
  1. 2021Megaverse: Simulating Embodied Agents at One Million Experiences per Secondcited by 19
  2. 2025Refined Policy Distillation: From VLA Generalists to RL Expertscited by 19
  3. 2021Learning Modular Robot Control Policiescited by 18
  4. 2024Stabilizing Reinforcement Learning in Differentiable Multiphysics Simulationcited by 14
  5. 2022A Survey on Reinforcement Learning Methods in Character Animationcited by 12
  6. 2025Stonefish: Supporting Machine Learning Research in Marine Roboticscited by 11
  7. 2025Learning Sim-to-Real Humanoid Locomotion in 15 Minutescited by 11
  8. 2021Improve Agents without Retraining: Parallel Tree Search with Off-Policy Correctioncited by 10
  9. 2022Fairness and Bias in Robot Learningcited by 10
  10. 2023Recent Advances of Deep Robotic Affordance Learning: A Reinforcement Learning Perspectivecited by 10
  11. 2025OceanSim: A GPU-Accelerated Underwater Robot Perception Simulation Frameworkcited by 10
  12. 2021Learning Visual Shape Control of Novel 3D Deformable Objects from Partial-View Point Cloudscited by 9
  13. 2025CEDex: Cross-Embodiment Dexterous Grasp Generation at Scale from Human-like Contact Representationscited by 9
  14. 2024Acceleration for Deep Reinforcement Learning using Parallel and Distributed Computing: A Surveycited by 8
  15. 2025Vintix: Action Model via In-Context Reinforcement Learningcited by 8
  16. 2025Kinematify: Open-Vocabulary Synthesis of High-DoF Articulated Objectscited by 8
  17. 2023Sim-Suction: Learning a Suction Grasp Policy for Cluttered Environments Using a Synthetic Benchmarkcited by 7
  18. 2025GAGrasp: Geometric Algebra Diffusion for Dexterous Graspingcited by 7
  19. 2025Digital Twin Generation from Visual Data: A Surveycited by 7
  20. 2024WheelPose: Data Synthesis Techniques to Improve Pose Estimation Performance on Wheelchair Userscited by 5
  21. 2025Differentiable Simulation of Hard Contacts with Soft Gradients for Learning and Controlcited by 5
  22. 2022Learning Behavior Representations Through Multi-Timescale Bootstrappingcited by 4
  23. 2023Relax, it doesn't matter how you get there: A new self-supervised approach for multi-timescale behavior analysiscited by 4
  24. 2023DeformerNet: Learning Bimanual Manipulation of 3D Deformable Objectscited by 4
  25. 2024Efficient Camera Exposure Control for Visual Odometry via Deep Reinforcement Learningcited by 4
  26. 2024GAPartManip: A Large-scale Part-centric Dataset for Material-Agnostic Articulated Object Manipulationcited by 4
  27. 2025Leveling the Playing Field: Carefully Comparing Classical and Learned Controllers for Quadrotor Trajectory Trackingcited by 4
  28. 2025InterAgent: Physics-based Multi-agent Command Execution via Diffusion on Interaction Graphscited by 4
  29. 2021DeformerNet: A Deep Learning Approach to 3D Deformable Object Manipulationcited by 3
  30. 2023DefGoalNet: Contextual Goal Learning from Demonstrations For Deformable Object Manipulationcited by 3
  31. 2024MARVIS: Motion & Geometry Aware Real and Virtual Image Segmentationcited by 3
  32. 2024Meta SAC-Lag: Towards Deployable Safe Reinforcement Learning via MetaGradient-based Hyperparameter Tuningcited by 3
  33. 2025FLoRA: Sample-Efficient Preference-based RL via Low-Rank Style Adaptation of Reward Functionscited by 3
  34. 2025MachaGrasp: Morphology-Aware Cross-Embodiment Dexterous Hand Articulation Generation for Graspingcited by 3
  35. 2026Let's Reward Step-by-Step: Step-Aware Contrastive Alignment for Vision-Language Navigation in Continuous Environmentscited by 3
  36. 2022Accelerating Robot Learning of Contact-Rich Manipulations: A Curriculum Learning Studycited by 2
  37. 2022Harfang3D Dog-Fight Sandbox: A Reinforcement Learning Research Platform for the Customized Control Tasks of Fighter Aircraftscited by 2
  38. 2024Reward Learning from Suboptimal Demonstrations with Applications in Surgical Electrocauterycited by 2

50 most cited of 77 All 77 (JSON)