mlsanityData to 7 Oct 2026

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

arXiv 2511.09737 ↗First posted 12 Nov 2025cs.LG cs.AIcited by 4

Not on the map. Why?

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.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 22 of its 27 references that are in the map. First posted on arXiv 12 Nov 2025.

Builds on

22 of 27 references.

References · 22

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  3. 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,401
  4. 2017Sim-to-Real Transfer of Robotic Control with Dynamics Randomizationcited by 616
  5. 2020Learning Quadrupedal Locomotion over Challenging Terraincited by 494
  6. 2016RL2: Fast Reinforcement Learning via Slow Reinforcement Learningcited by 490
  7. 2019Leveraging Procedural Generation to Benchmark Reinforcement Learningcited by 478
  8. 2020Reinforcement Learning with Augmented Datacited by 452
  9. 2021RMA: Rapid Motor Adaptation for Legged Robotscited by 430
  10. 2016Learning to reinforcement learncited by 369
  11. 2018Machine Theory of Mindcited by 222
  12. 2015Contextual Markov Decision Processescited by 213
10 more
  1. 2017Preparing for the Unknown: Learning a Universal Policy with Online System Identificationcited by 129
  2. 2021Stabilizing Deep Q-Learning with ConvNets and Vision Transformers under Data Augmentationcited by 101
  3. 2018Benchmarking Reinforcement Learning Algorithms on Real-World Robotscited by 64
  4. 2021Adversarial Reinforcement Learning for Procedural Content Generationcited by 36
  5. 2021Context-Aware Safe Reinforcement Learning for Non-Stationary Environmentscited by 33
  6. 2021CARL: A Benchmark for Contextual and Adaptive Reinforcement Learningcited by 21
  7. 2023Dynamics Generalisation in Reinforcement Learning via Adaptive Context-Aware Policiescited by 18
  8. 2024Dreaming of Many Worlds: Learning Contextual World Models Aids Zero-Shot Generalizationcited by 16
  9. 2023Fast Context Adaptation in Cost-Aware Continual Learningcited by 2
  10. 2023Composing Efficient, Robust Tests for Policy Selectioncited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026Contextual Intelligence The Next Leap for Reinforcement Learningcited by 1
  2. 2026Self-Paced Curriculum Reinforcement Learning for Autonomous Superbike Racing in Simulationcited by 0
  3. 2026Task Specialization Fine-Tuning for Contextual Reinforcement Learningcited by 0
  4. 2026Dynamic Context Scheduling: Learning Beyond the Static Universecited by 0