Out-of-Distribution Generalization with a SPARC: Racing 100 Unseen Vehicles with a Single Policy

Bram Grooten, Patrick MacAlpine, Kaushik Subramanian, Peter Stone, Peter R. Wurman
11/12/2025
cs.LGcs.AI

No official code found. Best implementation: bramgrooten/sparc (14 stars, MIT, last commit 2025-11-14).

Abstract

Generalization to unseen environments is a significant challenge in the field of robotics and control. In this work, we focus on contextual reinforcement learning, where agents act within environments with varying contexts, such as self-driving cars or quadrupedal robots that need to operate in different terrains or weather conditions than they were trained for. We tackle the critical task of generalizing to out-of-distribution (OOD) settings, without access to explicit context information at test time. Recent work has addressed this problem by training a context encoder and a history adaptation module in separate stages. While promising, this two-phase approach is cumbersome to implement and train. We simplify the methodology and introduce SPARC: single-phase adaptation for robust control. We test SPARC on varying contexts within the high-fidelity racing simulator Gran Turismo 7 and wind-perturbed MuJoCo environments, and find that it achieves reliable and robust OOD generalization.

View on arXivView PDF

Code Implementations(1)

bramgrooten/sparcCommunity66%
MIT

[AAAI 2026 Oral] Code for the oral paper "Out-of-Distribution Generalization with a SPARC: Racing 100 Unseen Vehicles with a Single Policy"

140PythonNov 11, 202511 months agoMIT
contextual-rlgeneralizationreinforcement-learning

Similar Papers

Context-Aware Model-Based Reinforcement Learning for Autonomous Racing

83% match2025

Diffusion Policies for Out-of-Distribution Generalization in Offline Reinforcement Learning

82% match1 repo32023

Can Agents Run Relay Race with Strangers? Generalization of RL to Out-of-Distribution Trajectories

80% match2023

GRAM: Generalization in Deep RL with a Robust Adaptation Module

80% match1 repo152024

Dynamics Generalisation in Reinforcement Learning via Adaptive Context-Aware Policies

79% match1 repo152026

Adapting by Analogy: OOD Generalization of Visuomotor Policies via Functional Correspondence

79% match2025

Cite this paper

@article{grooten2025outofdistribution,
  title  = {Out-of-Distribution Generalization with a SPARC: Racing 100 Unseen Vehicles with a Single Policy},
  author = {Bram Grooten and Patrick MacAlpine and Kaushik Subramanian and Peter Stone and Peter R. Wurman},
  year   = {2025},
  eprint = {2511.09737},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2511.09737v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2511.09737.svg)](https://codeofpaper.com/paper/2511.09737)

Discussion