Paper Detail

Continual-RL for Generalization in Autonomous Racing on the RoboRacer Platform

Joel Siegert, Edoardo Ghignone, Michele Magno

arxiv Score 8.5

Published 2026-07-27 · First seen 2026-07-28

Research Track A · General AI

Abstract

A key challenge in modern robotics is to adapt to changing environments, a challenge that is exacerbated when simulations cannot encompass every possible real-world configuration, and therefore Reinforcement Learning (RL) in the physical world becomes necessary. Continual Reinforcement Learning provides the tools to address this challenge; however, both the frameworks and the methods remain underexplored. Autonomous Racing and in particular the RoboRacer competition provide a testing ground for such methods, as learning to drive on a new track-floor combination with the least amount of new experience naturally frames a continual learning problem. This work tries to address this gap by proposing a continual RL framework based on Continual Backpropagation that is able, with only real-world data, to train a generalistic policy on a set of tracks and then fine- tune it within 15 minutes to outperform classical controllers. Furthermore, a comparison method based on offline RL is proposed, and a simulation analysis of the plasticity properties of the methods is conducted.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
soon
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{siegert2026continual,
  title = {Continual-RL for Generalization in Autonomous Racing on the RoboRacer Platform},
  author = {Joel Siegert and Edoardo Ghignone and Michele Magno},
  year = {2026},
  abstract = {A key challenge in modern robotics is to adapt to changing environments, a challenge that is exacerbated when simulations cannot encompass every possible real-world configuration, and therefore Reinforcement Learning (RL) in the physical world becomes necessary. Continual Reinforcement Learning provides the tools to address this challenge; however, both the frameworks and the methods remain underexplored. Autonomous Racing and in particular the RoboRacer competition provide a testing ground for },
  url = {https://arxiv.org/abs/2607.24320},
  keywords = {cs.RO, eess.SY},
  eprint = {2607.24320},
  archiveprefix = {arXiv},
}

Metadata

{}