Metraipolis › archive › dc_d4e5f4c754d1

Curriculum Generation under Structured Parametric Environments for Robust Navigation Policies — arXiv:2608.08545

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.08545
License (as archived)
CC0-1.0
Archived
2026-10-19T09:12:35.060Z
SHA-256 of the archived text
f47b0a83ead394e2a5ab89e5ee0850cc2cb0cb486f5d973453e82911e8a4f4a9
Stable URL of this page
https://metraipolis.com/documento/dc_d4e5f4c754d1

How to cite

Curriculum Generation under Structured Parametric Environments for Robust Navigation Policies — arXiv:2608.08545 — arXiv (en), https://arxiv.org/abs/2608.08545 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d4e5f4c754d1 (Metraipolis archive dc_d4e5f4c754d1, sha256 f47b0a83ead394e2a5ab89e5ee0850cc2cb0cb486f5d973453e82911e8a4f4a9)
BibTeX
@misc{dcd4e5f4c754d1,
  title = {Curriculum Generation under Structured Parametric Environments for Robust Navigation Policies — arXiv:2608.08545},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.08545},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d4e5f4c754d1; sha256 f47b0a83ead394e2a5ab89e5ee0850cc2cb0cb486f5d973453e82911e8a4f4a9},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.08545. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-11 in cs.RO).
Categorie arXiv: Robotics (cs.RO) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.08545 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-19T09:11:58.747Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-08-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).