mlsanityData to 14 Oct 2026

Analysis of Randomization Effects on Sim2Real Transfer in Reinforcement Learning for Robotic Manipulation Tasks

arXiv 2206.06282 ↗First posted 13 Jun 2022cs.RO cs.AIcited by 14

Not on the map. Why?

Abstract (arXiv)

Randomization is currently a widely used approach in Sim2Real transfer for data-driven learning algorithms in robotics. Still, most Sim2Real studies report results for a specific randomization technique and often on a highly customized robotic system, making it difficult to evaluate different randomization approaches systematically. To address this problem, we define an easy-to-reproduce experimental setup for a robotic reach-and-balance manipulator task, which can serve as a benchmark for comparison. We compare four randomization strategies with three randomized parameters both in simulation and on a real robot. Our results show that more randomization helps in Sim2Real transfer, yet it can also harm the ability of the algorithm to find a good policy in simulation. Fully randomized simulations and fine-tuning show differentiated results and translate better to the real robot than the other approaches tested.

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Builds on 18 of its 38 references that are in the map. First posted on arXiv 13 Jun 2022.

Builds on

18 of 38 references.

References · 18

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2013Playing Atari with Deep Reinforcement Learningcited by 3,274
  3. 2016OpenAI Gymcited by 1,736
  4. 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,498
  5. 2019Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learningcited by 1,204
  6. 2021Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learningcited by 998
  7. 2019Solving Rubik's Cube with a Robot Handcited by 734
  8. 2017Sim-to-Real Transfer of Robotic Control with Dynamics Randomizationcited by 672
  9. 2020Sim-to-Real Transfer in Deep Reinforcement Learning for Robotics: a Surveycited by 413
  10. 2018Sim-to-Real: Learning Agile Locomotion For Quadruped Robotscited by 319
  11. 2016Learning Hand-Eye Coordination for Robotic Grasping with Deep Learning and Large-Scale Data Collectioncited by 316
  12. 2019Emergent Tool Use From Multi-Agent Autocurriculacited by 313
6 more
  1. 2018Sim-to-Real via Sim-to-Sim: Data-efficient Robotic Grasping via Randomized-to-Canonical Adaptation Networkscited by 174
  2. 2016Sim-to-Real Robot Learning from Pixels with Progressive Netscited by 94
  3. 2021Robot Learning from Randomized Simulations: A Reviewcited by 63
  4. 2020Sim2Real Transfer for Reinforcement Learning without Dynamics Randomizationcited by 47
  5. 2016Towards MRI-Based Autonomous Robotic US Acquisitions: A First Feasibility Studycited by 29
  6. 20163D Simulation for Robot Arm Control with Deep Q-Learningcited by 21

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 5; 2024: 2; 2025: 6; 2026: 1.

14 papers.

Sort:

By area:

  1. 2023Domain Randomization via Entropy Maximizationcited by 19
  2. 2023Reproducibility of Machine Learning: Terminology, Recommendations and Open Issuescited by 8
  3. 2024Continual Domain Randomizationcited by 8
  4. 2023DiAReL: Reinforcement Learning with Disturbance Awareness for Robust Sim2Real Policy Transfer in Robot Controlcited by 7
  5. 2025One Net to Rule Them All: Domain Randomization in Quadcopter Racing Across Different Platformscited by 7
  6. 2025Flow-based Domain Randomization for Learning and Sequencing Robotic Skillscited by 4
  7. 2025Automatic Curriculum Learning for Driving Scenarios: Towards Robust and Efficient Reinforcement Learningcited by 3
  8. 2024Optimizing BioTac Simulation for Realistic Tactile Perceptioncited by 2
  9. 2025Safe Continual Domain Adaptation after Sim2Real Transfer of Reinforcement Learning Policies in Roboticscited by 2
  10. 2023State Representations as Incentives for Reinforcement Learning Agents: A Sim2Real Analysis on Robotic Graspingcited by 1
  11. 2025Shaken, Not Stirred: A Novel Dataset for Visual Understanding of Glasses in Human-Robot Bartending Taskscited by 1
  12. 2026Tac2Real: Reliable and GPU Visuotactile Simulation for Online Reinforcement Learning and Zero-Shot Real-World Deploymentcited by 1
2 more
  1. 2023Bird's Eye View Based Pretrained World model for Visual Navigationcited by 0
  2. 2025Multimodal Fusion for Sim2real Transfer in Visual Reinforcement Learningcited by 0