Safe Continual Domain Adaptation after Sim2Real Transfer of Reinforcement Learning Policies in Robotics Article Swipe

MAKE IMPACT

Josip Josifovski , Shangding Gu , Mohammadhossein Malmir , Haoliang Huang , Sayantan Auddy , Nicolás Navarro-Guerrero , Costas J. Spanos , Alois Knoll · YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2503.10949

Domain randomization has emerged as a fundamental technique in reinforcement learning (RL) to facilitate the transfer of policies from simulation to real-world robotic applications. Many existing domain randomization approaches have been proposed to improve robustness and sim2real transfer. These approaches rely on wide randomization ranges to compensate for the unknown actual system parameters, leading to robust but inefficient real-world policies. In addition, the policies pretrained in the domain-randomized simulation are fixed after deployment due to the inherent instability of the optimization processes based on RL and the necessity of sampling exploitative but potentially unsafe actions on the real system. This limits the adaptability of the deployed policy to the inevitably changing system parameters or environment dynamics over time. We leverage safe RL and continual learning under domain-randomized simulation to address these limitations and enable safe deployment-time policy adaptation in real-world robot control. The experiments show that our method enables the policy to adapt and fit to the current domain distribution and environment dynamics of the real system while minimizing safety risks and avoiding issues like catastrophic forgetting of the general policy found in randomized simulation during the pretraining phase. Videos and supplementary material are available at https://safe-cda.github.io/.

Type

preprint

Language

en

Landing Page

http://arxiv.org/abs/2503.10949

PDF

https://arxiv.org/pdf/2503.10949

OA Status

green

OpenAlex ID

https://openalex.org/W4417281717

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W4417281717

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2503.10949

Digital Object Identifier

Title

Safe Continual Domain Adaptation after Sim2Real Transfer of Reinforcement Learning Policies in Robotics

Work title

Type

preprint

OpenAlex work type

Language

en

Primary language

Publication year

2025

Year of publication

Publication date

2025-03-13

Full publication date if available

Authors

Josip Josifovski, Shangding Gu, Mohammadhossein Malmir, Haoliang Huang, Sayantan Auddy, Nicolás Navarro-Guerrero, Costas J. Spanos, Alois Knoll

List of authors in order

Landing page

https://arxiv.org/abs/2503.10949

Publisher landing page

PDF URL

https://arxiv.org/pdf/2503.10949

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2503.10949

Direct OA link when available

Cited by

0

Total citation count in OpenAlex

Full payload