# Active Domain Randomization

arXiv: https://arxiv.org/abs/1904.04762 · HTML: https://mlsanity.com/paper/1904.04762/

## Key facts

- Cited by 170 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Apr 2019.

## Built on by (most cited first, 30 of 170)

- [BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learning](https://mlsanity.com/paper/2202.02005/) (2022)
- [Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learning](https://mlsanity.com/paper/2108.06266/) (2021)
- [Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts](https://mlsanity.com/paper/2402.16822/) (2024)
- [Scaling Robot Learning with Semantically Imagined Experience](https://mlsanity.com/paper/2302.11550/) (2023)
- [Evolving Curricula with Regret-Based Environment Design](https://mlsanity.com/paper/2203.01302/) (2022)
- [THE COLOSSEUM: A Benchmark for Evaluating Generalization for Robotic Manipulation](https://mlsanity.com/paper/2402.08191/) (2024)
- [Replay-Guided Adversarial Environment Design](https://mlsanity.com/paper/2110.02439/) (2021)
- [RORL: Robust Offline Reinforcement Learning via Conservative Smoothing](https://mlsanity.com/paper/2206.02829/) (2022)
- [DrEureka: Language Model Guided Sim-To-Real Transfer](https://mlsanity.com/paper/2406.01967/) (2024)
- [EquiBot: SIM(3)-Equivariant Diffusion Policy for Generalizable and Data Efficient Learning](https://mlsanity.com/paper/2407.01479/) (2024)
- [Robot Learning from Randomized Simulations: A Review](https://mlsanity.com/paper/2111.00956/) (2021)
- [Contextualize Me -- The Case for Context in Reinforcement Learning](https://mlsanity.com/paper/2202.04500/) (2022)
- [Sim-and-Real Co-Training: A Simple Recipe for Vision-Based Robotic Manipulation](https://mlsanity.com/paper/2503.24361/) (2025)
- [A Survey of Sim-to-Real Methods in RL: Progress, Prospects and Challenges with Foundation Models](https://mlsanity.com/paper/2502.13187/) (2025)
- [EquivAct: SIM(3)-Equivariant Visuomotor Policies beyond Rigid Object Manipulation](https://mlsanity.com/paper/2310.16050/) (2023)
- [Trustworthy Reinforcement Learning Against Intrinsic Vulnerabilities: Robustness, Safety, and Generalizability](https://mlsanity.com/paper/2209.08025/) (2022)
- [Generalizing Goal-Conditioned Reinforcement Learning with Variational Causal Reasoning](https://mlsanity.com/paper/2207.09081/) (2022)
- [Environment Generation for Zero-Shot Compositional Reinforcement Learning](https://mlsanity.com/paper/2201.08896/) (2022)
- [DiffCloud: Real-to-Sim from Point Clouds with Differentiable Simulation and Rendering of Deformable Objects](https://mlsanity.com/paper/2204.03139/) (2022)
- [Cross-Domain Policy Adaptation via Value-Guided Data Filtering](https://mlsanity.com/paper/2305.17625/) (2023)
- [Curriculum Reinforcement Learning using Optimal Transport via Gradual Domain Adaptation](https://mlsanity.com/paper/2210.10195/) (2022)
- [ISAACS: Iterative Soft Adversarial Actor-Critic for Safety](https://mlsanity.com/paper/2212.03228/) (2022)
- [MoDem-V2: Visuo-Motor World Models for Real-World Robot Manipulation](https://mlsanity.com/paper/2309.14236/) (2023)
- [ASID: Active Exploration for System Identification in Robotic Manipulation](https://mlsanity.com/paper/2404.12308/) (2024)
- [HuB: Learning Extreme Humanoid Balance](https://mlsanity.com/paper/2505.07294/) (2025)
- [Sim-to-Lab-to-Real: Safe Reinforcement Learning with Shielding and Generalization Guarantees](https://mlsanity.com/paper/2201.08355/) (2022)
- [Variational Automatic Curriculum Learning for Sparse-Reward Cooperative Multi-Agent Problems](https://mlsanity.com/paper/2111.04613/) (2021)
- [FuRL: Visual-Language Models as Fuzzy Rewards for Reinforcement Learning](https://mlsanity.com/paper/2406.00645/) (2024)
- [Seeing is not Believing: Robust Reinforcement Learning against Spurious Correlation](https://mlsanity.com/paper/2307.07907/) (2023)
- [Cross-Domain Policy Adaptation by Capturing Representation Mismatch](https://mlsanity.com/paper/2405.15369/) (2024)

## 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.