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

arXiv: https://arxiv.org/abs/2511.09737 · HTML: https://mlsanity.com/paper/2511.09737/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 27 references that are in the map.
- First posted on arXiv 12 Nov 2025.

## Builds on (most cited first, 22 of 22)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World](https://mlsanity.com/paper/1703.06907/) (2017)
- [Sim-to-Real Transfer of Robotic Control with Dynamics Randomization](https://mlsanity.com/paper/1710.06537/) (2017)
- [Learning Quadrupedal Locomotion over Challenging Terrain](https://mlsanity.com/paper/2010.11251/) (2020)
- [RMA: Rapid Motor Adaptation for Legged Robots](https://mlsanity.com/paper/2107.04034/) (2021)
- [RL2: Fast Reinforcement Learning via Slow Reinforcement Learning](https://mlsanity.com/paper/1611.02779/) (2016)
- [Leveraging Procedural Generation to Benchmark Reinforcement Learning](https://mlsanity.com/paper/1912.01588/) (2019)
- [Reinforcement Learning with Augmented Data](https://mlsanity.com/paper/2004.14990/) (2020)
- [Learning to reinforcement learn](https://mlsanity.com/paper/1611.05763/) (2016)
- [Machine Theory of Mind](https://mlsanity.com/paper/1802.07740/) (2018)
- [Contextual Markov Decision Processes](https://mlsanity.com/paper/1502.02259/) (2015)
- [Preparing for the Unknown: Learning a Universal Policy with Online System Identification](https://mlsanity.com/paper/1702.02453/) (2017)
- [Stabilizing Deep Q-Learning with ConvNets and Vision Transformers under Data Augmentation](https://mlsanity.com/paper/2107.00644/) (2021)
- [Benchmarking Reinforcement Learning Algorithms on Real-World Robots](https://mlsanity.com/paper/1809.07731/) (2018)
- [Adversarial Reinforcement Learning for Procedural Content Generation](https://mlsanity.com/paper/2103.04847/) (2021)
- [Context-Aware Safe Reinforcement Learning for Non-Stationary Environments](https://mlsanity.com/paper/2101.00531/) (2021)
- [CARL: A Benchmark for Contextual and Adaptive Reinforcement Learning](https://mlsanity.com/paper/2110.02102/) (2021)
- [Dynamics Generalisation in Reinforcement Learning via Adaptive Context-Aware Policies](https://mlsanity.com/paper/2310.16686/) (2023)
- [Dreaming of Many Worlds: Learning Contextual World Models Aids Zero-Shot Generalization](https://mlsanity.com/paper/2403.10967/) (2024)
- [Fast Context Adaptation in Cost-Aware Continual Learning](https://mlsanity.com/paper/2306.03887/) (2023)
- [Composing Efficient, Robust Tests for Policy Selection](https://mlsanity.com/paper/2306.07372/) (2023)

## Built on by (most cited first, 5 of 5)

- [Contextual Intelligence The Next Leap for Reinforcement Learning](https://mlsanity.com/paper/2604.02348/) (2026)
- [Dynamics Distillation for Efficient and Transferable Control Learning](https://mlsanity.com/paper/2605.01516/) (2026)
- [Self-Paced Curriculum Reinforcement Learning for Autonomous Superbike Racing in Simulation](https://mlsanity.com/paper/2606.09236/) (2026)
- [Task Specialization Fine-Tuning for Contextual Reinforcement Learning](https://mlsanity.com/paper/2608.17180/) (2026)
- [Dynamic Context Scheduling: Learning Beyond the Static Universe](https://mlsanity.com/paper/2608.20799/) (2026)

## Abstract (arXiv)

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.