mlsanityData to 7 Oct 2026

Active Domain Randomization

arXiv 1904.04762 ↗First posted 9 Apr 2019cs.LG cs.AI cs.ROcited by 161

Not on the map. Why?

Abstract (arXiv)

Domain randomization is a popular technique for improving domain transfer, often used in a zero-shot setting when the target domain is unknown or cannot easily be used for training. In this work, we empirically examine the effects of domain randomization on agent generalization. Our experiments show that domain randomization may lead to suboptimal, high-variance policies, which we attribute to the uniform sampling of environment parameters. We propose Active Domain Randomization, a novel algorithm that learns a parameter sampling strategy. Our method looks for the most informative environment variations within the given randomization ranges by leveraging the discrepancies of policy rollouts in randomized and reference environment instances. We find that training more frequently on these instances leads to better overall agent generalization. Our experiments across various physics-based simulated and real-robot tasks show that this enhancement leads to more robust, consistent policies.

Key facts. Cited by 161 papers in the map (data through 7 Oct 2026). First posted on arXiv 9 Apr 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 25; 2022: 29; 2023: 23; 2024: 25; 2025: 36; 2026: 23.

161 papers.

Sort:

By area:

  1. 2022BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learningcited by 517
  2. 2021Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learningcited by 337
  3. 2024Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Promptscited by 189
  4. 2023Scaling Robot Learning with Semantically Imagined Experiencecited by 175
  5. 2022Evolving Curricula with Regret-Based Environment Designcited by 166
  6. 2024THE COLOSSEUM: A Benchmark for Evaluating Generalization for Robotic Manipulationcited by 128
  7. 2021Replay-Guided Adversarial Environment Designcited by 108
  8. 2022RORL: Robust Offline Reinforcement Learning via Conservative Smoothingcited by 83
  9. 2024DrEureka: Language Model Guided Sim-To-Real Transfercited by 78
  10. 2024EquiBot: SIM(3)-Equivariant Diffusion Policy for Generalizable and Data Efficient Learningcited by 72
  11. 2021Robot Learning from Randomized Simulations: A Reviewcited by 56
  12. 2025Sim-and-Real Co-Training: A Simple Recipe for Vision-Based Robotic Manipulationcited by 42
38 more
  1. 2022Contextualize Me -- The Case for Context in Reinforcement Learningcited by 41
  2. 2023EquivAct: SIM(3)-Equivariant Visuomotor Policies beyond Rigid Object Manipulationcited by 37
  3. 2025A Survey of Sim-to-Real Methods in RL: Progress, Prospects and Challenges with Foundation Modelscited by 36
  4. 2022Generalizing Goal-Conditioned Reinforcement Learning with Variational Causal Reasoningcited by 33
  5. 2022Environment Generation for Zero-Shot Compositional Reinforcement Learningcited by 32
  6. 2022Trustworthy Reinforcement Learning Against Intrinsic Vulnerabilities: Robustness, Safety, and Generalizabilitycited by 32
  7. 2023Cross-Domain Policy Adaptation via Value-Guided Data Filteringcited by 30
  8. 2022DiffCloud: Real-to-Sim from Point Clouds with Differentiable Simulation and Rendering of Deformable Objectscited by 29
  9. 2022Curriculum Reinforcement Learning using Optimal Transport via Gradual Domain Adaptationcited by 28
  10. 2023MoDem-V2: Visuo-Motor World Models for Real-World Robot Manipulationcited by 27
  11. 2024ASID: Active Exploration for System Identification in Robotic Manipulationcited by 27
  12. 2024FuRL: Visual-Language Models as Fuzzy Rewards for Reinforcement Learningcited by 26
  13. 2021Variational Automatic Curriculum Learning for Sparse-Reward Cooperative Multi-Agent Problemscited by 25
  14. 2023Seeing is not Believing: Robust Reinforcement Learning against Spurious Correlationcited by 25
  15. 2024ODRL: A Benchmark for Off-Dynamics Reinforcement Learningcited by 25
  16. 2022Sim-to-Lab-to-Real: Safe Reinforcement Learning with Shielding and Generalization Guaranteescited by 24
  17. 2022ISAACS: Iterative Soft Adversarial Actor-Critic for Safetycited by 24
  18. 2024Cross-Domain Policy Adaptation by Capturing Representation Mismatchcited by 24
  19. 2022You Only Live Once: Single-Life Reinforcement Learningcited by 23
  20. 2025PIN-WM: Learning Physics-INformed World Models for Non-Prehensile Manipulationcited by 22
  21. 2025HuB: Learning Extreme Humanoid Balancecited by 21
  22. 2025Model Predictive Task Sampling for Efficient and Robust Adaptationcited by 20
  23. 2021TeachMyAgent: a Benchmark for Automatic Curriculum Learning in Deep RLcited by 18
  24. 2021Distributionally Robust Policy Learning via Adversarial Environment Generationcited by 17
  25. 2021Probabilistic Inference of Simulation Parameters via Parallel Differentiable Simulationcited by 17
  26. 2024Overcoming the Sim-to-Real Gap: Leveraging Simulation to Learn to Explore for Real-World RLcited by 17
  27. 2022DROPO: Sim-to-Real Transfer with Offline Domain Randomizationcited by 16
  28. 2022Robust Policy Learning over Multiple Uncertainty Setscited by 16
  29. 2024A Comprehensive Survey of Cross-Domain Policy Transfer for Embodied Agentscited by 16
  30. 2023H2O+: An Improved Framework for Hybrid Offline-and-Online RL with Dynamics Gapscited by 15
  31. 2023Domain Randomization via Entropy Maximizationcited by 15
  32. 2024KALIE: Fine-Tuning Vision-Language Models for Open-World Manipulation without Robot Datacited by 15
  33. 2023Reward-Free Curricula for Training Robust World Modelscited by 13
  34. 2023Rapid Motor Adaptation for Robotic Manipulator Armscited by 13
  35. 2024Robust Fast Adaptation from Adversarially Explicit Task Distribution Generationcited by 12
  36. 2021A Bayesian Treatment of Real-to-Sim for Deformable Object Manipulationcited by 11
  37. 2022Max-Min Off-Policy Actor-Critic Method Focusing on Worst-Case Robustness to Model Misspecificationcited by 11
  38. 2025Fast and Robust: Task Sampling with Posterior and Diversity Synergies for Adaptive Decision-Makers in Randomized Environmentscited by 11

50 most cited of 161 All 161 (JSON)