# Continual Domain Randomization Source: [Continual Domain Randomization]() Collection index: [llms.txt]() Data updated: 2026-04-30T05:00:04.703Z Authors: Josip Josifovski, Sayantan Auddy, Mohammadhossein Malmir, Justus Piater, Alois Knoll, Nicol\\'as Navarro-Guerrero Published: 2024-03-18T19:04:56.000Z ## Abstract Domain Randomization (DR) is commonly used for sim2real transfer of reinforcement learning (RL) policies in robotics. Most DR approaches require a simulator with a fixed set of tunable parameters from the start of the training, from which the parameters are randomized simultaneously to train a robust model for use in the real world. However, the combined randomization of many parameters increases the task difficulty and might result in sub-optimal policies. To address this problem and to provide a more flexible training process, we propose Continual Domain Randomization (CDR) for RL that combines domain randomization with continual learning to enable sequential training in simulation on a subset of randomization parameters at a time. Starting from a model trained in a non-randomized simulation where the task is easier to solve, the model is trained on a sequence of randomizations, and continual learning is employed to remember the effects of previous randomizations. Our robotic reaching and grasping tasks experiments show that the model trained in this fashion learns effectively in simulation and performs robustly on the real robot while matching or outperforming baselines that employ combined randomization or sequential randomization without continual learning. Our code and videos are available at https://continual-dr.github.io/. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Reaching on Reacher Simulation](): Reaching; Reacher Simulation; Repetition Metric: -140.59. - [Reaching on Reacher Reality](): Reaching; Reacher Reality; Completion Rate Score: -143.88. - [Grasping on Robot Grasping Simulation](): Grasping; Robot Grasping Simulation; Episodic Reward: -12.74. - [Robot Grasping Real World](): Grasping; Robot Grasping Real World; Episodic Reward (rep): -22.78. ## Original sources and implementation [Original paper]() [PDF]()