mlsanityData to 7 Oct 2026

Curriculum Generation under Structured Parametric Environments for Robust Navigation Policies

arXiv 2608.08545 ↗First posted 9 Aug 2026cs.RO cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Robust navigation policies for autonomous agents must generalize across continuously varying environmental conditions such as turn rates, obstacles, friction, pits, and slopes. Curriculum generation provides a principled mechanism for improving generalization by progressively adapting training environments, but designing such curricula in a sample-efficient and automated manner remains challenging. This paper proposes a reparameterized curriculum generation framework for structured continuous environment parameters using unidirectional gradient-based optimization. To improve robustness in multimodal observation spaces consisting of image-based and scalar inputs, a distribution-shift regularization objective is incorporated to encourage the learning of finer-grained latent representations. The proposed method is evaluated across two continuous-control OpenAI Gym environments: a 2D obstacle-based Car Racing variant and Bipedal Walker variant, where coupled environment parameters jointly influence policy performance. Across five random seeds, our method consistently outperforms vanilla policy training, random parameter sampling, manual curricula, frontier-based methods, Self-Paced Reinforcement Learning (SPRL), Absolute Learning Progress with Gaussian Mixture Models (ALP-GMM), and reverse curriculum learning baselines. Ablation studies further demonstrate the effectiveness of the reparameterized curriculum mechanism across both environments, while highlighting environment-dependent benefits of the auxiliary regularization objective.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 21 of its 28 references that are in the map. First posted on arXiv 9 Aug 2026.

Builds on

21 of 28 references.

References · 21

  1. 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,401
  2. 2019Leveraging Procedural Generation to Benchmark Reinforcement Learningcited by 478
  3. 2017Robust Adversarial Reinforcement Learningcited by 439
  4. 2020Curriculum Learning for Reinforcement Learning Domains: A Framework and Surveycited by 350
  5. 2020Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Designcited by 260
  6. 2017Teacher-Student Curriculum Learningcited by 197
  7. 2020Prioritized Level Replaycited by 190
  8. 2019Paired Open-Ended Trailblazer (POET): Endlessly Generating Increasingly Complex and Diverse Learning Environments and Their Solutionscited by 182
  9. 2022Evolving Curricula with Regret-Based Environment Designcited by 166
  10. 2020Automatic Curriculum Learning For Deep RL: A Short Surveycited by 141
  11. 2019Teacher algorithms for curriculum learning of Deep RL in continuously parameterized environmentscited by 113
  12. 2021Replay-Guided Adversarial Environment Designcited by 108
9 more
  1. 2020Robust Reinforcement Learning using Adversarial Populationscited by 64
  2. 2020Self-Paced Deep Reinforcement Learningcited by 49
  3. 2022CLUTR: Curriculum Learning via Unsupervised Task Representation Learningcited by 19
  4. 2024CurricuLLM: Automatic Task Curricula Design for Learning Complex Robot Skills using Large Language Modelscited by 19
  5. 2021Distributionally Robust Policy Learning via Adversarial Environment Generationcited by 17
  6. 2022Robust Reinforcement Learning via Genetic Curriculumcited by 10
  7. 2022ACuTE: Automatic Curriculum Transfer from Simple to Complex Environmentscited by 7
  8. 2023Improving Environment Robustness of Deep Reinforcement Learning Approaches for Autonomous Racing Using Bayesian Optimization-based Curriculum Learningcited by 2
  9. 2024Syllabus: Portable Curricula for Reinforcement Learning Agentscited by 2

Built on by

Not cited yet.