Online vs. Offline Adaptive Domain Randomization Benchmark

Gabriele Tiboni*, Karol Arndt, Giuseppe Averta, Ville Kyrki, Tatiana Tommasi

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review


Physics simulators have shown great promise for conveniently learning reinforcement learning policies in safe, unconstrained environments. However, transferring the acquired knowledge to the real world can be challenging due to the reality gap. To this end, several methods have been recently proposed to automatically tune simulator parameters with posterior distributions given real data, for use with domain randomization at training time. These approaches have been shown to work for various robotic tasks under different settings and assumptions. Nevertheless, existing literature lacks a thorough comparison of existing adaptive domain randomization methods with respect to transfer performance and real-data efficiency. This work presents an open benchmark for both offline and online methods (SimOpt, BayRn, DROID, DROPO), to investigate current limitations on multiple settings and tasks. We found that online methods are limited by the quality of the currently learned policy for the next iteration, while offline methods may sometimes fail when replaying trajectories in simulation with open-loop commands. The code used is publicly available at

Original languageEnglish
Title of host publicationHuman-Friendly Robotics 2022 - HFR
Subtitle of host publication15th International Workshop on Human-Friendly Robotics
EditorsPablo Borja, Cosimo Della Santina, Luka Peternel, Elena Torta
Number of pages16
ISBN (Electronic)978-3-031-22731-8
ISBN (Print)978-3-031-22730-1
Publication statusPublished - 2023
MoE publication typeA4 Conference publication
EventInternational Workshop on Human-Friendly Robotics - Delft, Netherlands
Duration: 22 Sept 202223 Sept 2022

Publication series

NameSpringer Proceedings in Advanced Robotics
ISSN (Print)2511-1256
ISSN (Electronic)2511-1264


WorkshopInternational Workshop on Human-Friendly Robotics
Abbreviated titleHFR


  • Benchmark
  • Domain randomization
  • Robot learning
  • Sim-to-real


Dive into the research topics of 'Online vs. Offline Adaptive Domain Randomization Benchmark'. Together they form a unique fingerprint.

Cite this