mlsanityData to 7 Oct 2026

Dynamics Randomization Revisited:A Case Study for Quadrupedal Locomotion

arXiv 2011.02404 ↗First posted 4 Nov 2020cs.ROcited by 54

Not on the map. Why?

Abstract (arXiv)

Understanding the gap between simulation and reality is critical for reinforcement learning with legged robots, which are largely trained in simulation. However, recent work has resulted in sometimes conflicting conclusions with regard to which factors are important for success, including the role of dynamics randomization. In this paper, we aim to provide clarity and understanding on the role of dynamics randomization in learning robust locomotion policies for the Laikago quadruped robot. Surprisingly, in contrast to prior work with the same robot model, we find that direct sim-to-real transfer is possible without dynamics randomization or on-robot adaptation schemes. We conduct extensive ablation studies in a sim-to-sim setting to understand the key issues underlying successful policy transfer, including other design decisions that can impact policy robustness. We further ground our conclusions via sim-to-real experiments with various gaits, speeds, and stepping frequencies. Additional Details: https://www.pair.toronto.edu/understanding-dr/.

Key facts. Cited by 54 papers in the map (data through 7 Oct 2026). First posted on arXiv 4 Nov 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 13; 2022: 9; 2023: 11; 2024: 11; 2025: 8; 2026: 2.

54 papers.

Sort:

By area:

  1. 2021RMA: Rapid Motor Adaptation for Legged Robotscited by 430
  2. 2024Deep Reinforcement Learning for Robotics: A Survey of Real-World Successescited by 153
  3. 2022Legged Locomotion in Challenging Terrains using Egocentric Visioncited by 131
  4. 2022Rapid Locomotion via Reinforcement Learningcited by 130
  5. 2023Robot Parkour Learningcited by 115
  6. 2024DrEureka: Language Model Guided Sim-To-Real Transfercited by 78
  7. 2021Learning Vision-Guided Quadrupedal Locomotion End-to-End with Cross-Modal Transformerscited by 71
  8. 2024Reinforcement Learning for Versatile, Dynamic, and Robust Bipedal Locomotion Controlcited by 63
  9. 2021Robot Learning from Randomized Simulations: A Reviewcited by 56
  10. 2021Coupling Vision and Proprioception for Navigation of Legged Robotscited by 46
  11. 2023DribbleBot: Dynamic Legged Manipulation in the Wildcited by 33
  12. 2023Barkour: Benchmarking Animal-level Agility with Quadruped Robotscited by 33
38 more
  1. 2025BeamDojo: Learning Agile Humanoid Locomotion on Sparse Footholdscited by 32
  2. 2023Hybrid Internal Model: Learning Agile Legged Locomotion with Simulated Robot Responsecited by 31
  3. 2022Imitate and Repurpose: Learning Reusable Robot Movement Skills From Human and Animal Behaviorscited by 27
  4. 2021GLiDE: Generalizable Quadrupedal Locomotion in Diverse Environments with a Centroidal Modelcited by 23
  5. 2022Learning Torque Control for Quadrupedal Locomotioncited by 22
  6. 2021Robust High-speed Running for Quadruped Robots via Deep Reinforcement Learningcited by 20
  7. 2021Vision-Guided Quadrupedal Locomotion in the Wild with Multi-Modal Delay Randomizationcited by 18
  8. 2021Value Iteration in Continuous Actions, States and Timecited by 17
  9. 2024World Model-based Perception for Visual Legged Locomotioncited by 17
  10. 2021Model-free Reinforcement Learning for Robust Locomotion using Demonstrations from Trajectory Optimizationcited by 16
  11. 2022Learning and Deploying Robust Locomotion Policies with Minimal Dynamics Randomizationcited by 15
  12. 2024Commonsense Reasoning for Legged Robot Adaptation with Vision-Language Modelscited by 15
  13. 2022Sim-to-Real Transfer for Quadrupedal Locomotion via Terrain Transformercited by 12
  14. 2023Learning Risk-Aware Quadrupedal Locomotion using Distributional Reinforcement Learningcited by 12
  15. 2024CaT: Constraints as Terminations for Legged Locomotion Reinforcement Learningcited by 11
  16. 2025Bridging the Sim-to-Real Gap for Athletic Loco-Manipulationcited by 11
  17. 2021Reinforcement Learning with Evolutionary Trajectory Generator: A General Approach for Quadrupedal Locomotioncited by 10
  18. 2024Rethinking Robustness Assessment: Adversarial Attacks on Learning-based Quadrupedal Locomotion Controllerscited by 9
  19. 2021Robust Value Iteration for Continuous Control Taskscited by 8
  20. 2023Bridging the Sim-to-Real Gap from the Information Bottleneck Perspectivecited by 8
  21. 2022Learning Low-Frequency Motion Control for Robust and Dynamic Robot Locomotioncited by 7
  22. 2023Learning Robust, Agile, Natural Legged Locomotion Skills in the Wildcited by 7
  23. 2023Adapt On-the-Go: Behavior Modulation for Single-Life Robot Deploymentcited by 7
  24. 2021Continuous-Time Fitted Value Iteration for Robust Policiescited by 6
  25. 2025Unsupervised Skill Discovery as Exploration for Learning Agile Locomotioncited by 5
  26. 2023Identifying Important Sensory Feedback for Learning Locomotion Skillscited by 4
  27. 2023Pay Attention to How You Drive: Safe and Adaptive Model-Based Reinforcement Learning for Off-Road Drivingcited by 4
  28. 2025LocoMamba: Vision-Driven Locomotion via End-to-End Deep Reinforcement Learning with Mambacited by 3
  29. 2023BayRnTune: Adaptive Bayesian Domain Randomization via Strategic Fine-tuningcited by 2
  30. 2024An Efficient Model-Based Approach on Learning Agile Motor Skills without Reinforcementcited by 2
  31. 2026Learning Gait-Aware Quadruped Locomotion with Temporal Logic Specificationscited by 2
  32. 2022Open-Ended Diverse Solution Discovery with Regulated Behavior Patterns for Cross-Domain Adaptationcited by 1
  33. 2024Learning Emergent Gaits with Decentralized Phase Oscillators: on the role of Observations, Rewards, and Feedbackcited by 1
  34. 2024LoopSR: Looping Sim-and-Real for Lifelong Policy Adaptation of Legged Robotscited by 1
  35. 2021PM-FSM: Policies Modulating Finite State Machine for Robust Quadrupedal Locomotioncited by 0
  36. 2022Quantification before Selection: Active Dynamics Preference for Robust Reinforcement Learningcited by 0
  37. 2024Impedance Matching: Enabling an RL-Based Running Jump in a Quadruped Robotcited by 0
  38. 2025Variable Stiffness for Robust Locomotion through Reinforcement Learningcited by 0

50 most cited of 54 All 54 (JSON)