mlsanityData to 14 Oct 2026

BayRnTune: Adaptive Bayesian Domain Randomization via Strategic Fine-tuning

arXiv 2310.10606 ↗First posted 16 Oct 2023cs.RO cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

Domain randomization (DR), which entails training a policy with randomized dynamics, has proven to be a simple yet effective algorithm for reducing the gap between simulation and the real world. However, DR often requires careful tuning of randomization parameters. Methods like Bayesian Domain Randomization (Bayesian DR) and Active Domain Randomization (Adaptive DR) address this issue by automating parameter range selection using real-world experience. While effective, these algorithms often require long computation time, as a new policy is trained from scratch every iteration. In this work, we propose Adaptive Bayesian Domain Randomization via Strategic Fine-tuning (BayRnTune), which inherits the spirit of BayRn but aims to significantly accelerate the learning processes by fine-tuning from previously learned policy. This idea leads to a critical question: which previous policy should we use as a prior during fine-tuning? We investigated four different fine-tuning strategies and compared them against baseline algorithms in five simulated environments, ranging from simple benchmark tasks to more complex legged robot environments. Our analysis demonstrates that our method yields better rewards in the same amount of timesteps compared to vanilla domain randomization or Bayesian DR.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 28 of its 37 references that are in the map. First posted on arXiv 16 Oct 2023.

Builds on

28 of 37 references.

References · 28

  1. 2016OpenAI Gymcited by 1,736
  2. 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,498
  3. 2021Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learningcited by 998
  4. 2019Solving Rubik's Cube with a Robot Handcited by 734
  5. 2017Sim-to-Real Transfer of Robotic Control with Dynamics Randomizationcited by 672
  6. 2021RMA: Rapid Motor Adaptation for Legged Robotscited by 508
  7. 2019Learning agile and dynamic motor skills for legged robotscited by 504
  8. 2018Sim-to-Real: Learning Agile Locomotion For Quadruped Robotscited by 319
  9. 2020Learning Agile Robotic Locomotion Skills by Imitating Animalscited by 251
  10. 2018Closing the Sim-to-Real Loop: Adapting Simulation Randomization with Real World Experiencecited by 217
  11. 2019Active Domain Randomizationcited by 170
  12. 2018Learning to Walk via Deep Reinforcement Learningcited by 158
16 more
  1. 2017Preparing for the Unknown: Learning a Universal Policy with Online System Identificationcited by 141
  2. 2019TossingBot: Learning to Throw Arbitrary Objects with Residual Physicscited by 137
  3. 2020Learning to Walk in the Real World with Minimal Human Effortcited by 111
  4. 2021Blind Bipedal Stair Traversal via Sim-to-Real Reinforcement Learningcited by 92
  5. 2019BayesSim: adaptive domain randomization via probabilistic inference for robotics simulatorscited by 85
  6. 2022Neural-Fly Enables Rapid Learning for Agile Flight in Strong Windscited by 85
  7. 2021Legged Robots that Keep on Learning: Fine-Tuning Locomotion Policies in the Real Worldcited by 71
  8. 2019Data Efficient Reinforcement Learning for Legged Robotscited by 63
  9. 2020Dynamics Randomization Revisited:A Case Study for Quadrupedal Locomotioncited by 59
  10. 2019Sim-to-Real Transfer for Biped Locomotioncited by 56
  11. 2021Auto-Tuned Sim-to-Real Transfercited by 49
  12. 2019Learning Fast Adaptation with Meta Strategy Optimizationcited by 48
  13. 2020Data-efficient Domain Randomization with Bayesian Optimizationcited by 47
  14. 2019TuneNet: One-Shot Residual Tuning for System Identification and Sim-to-Real Robot Task Transfercited by 22
  15. 2022Cascaded Compositional Residual Learning for Complex Interactive Behaviorscited by 10
  16. 2023Residual Physics Learning and System Identification for Sim-to-real Transfer of Policies on Buoyancy Assisted Legged Robotscited by 8

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 2.

3 papers.

  1. 2024Learning Multi-Agent Loco-Manipulation for Long-Horizon Quadrupedal Pushingcited by 13
  2. 2025Human2LocoMan: Learning Versatile Quadrupedal Manipulation with Human Pretrainingcited by 9
  3. 2025Mechanical Intelligence-Aware Curriculum Reinforcement Learning for Humanoids with Parallel Actuationcited by 1