Metraipolis › archive › dc_28754d0ee511

Scaling Curriculum Learning For Autonomous Driving — arXiv:2608.22549

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.22549
License (as archived): CC0-1.0
Archived: 2026-10-18T07:41:30.051Z
SHA-256 of the archived text: 96cba06b24080125c462cf1fe20d05148316830805bb075b6b65f78783019e11
Stable URL of this page: https://metraipolis.com/documento/dc_28754d0ee511

How to cite

Scaling Curriculum Learning For Autonomous Driving — arXiv:2608.22549 — arXiv (en), https://arxiv.org/abs/2608.22549 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_28754d0ee511 (Metraipolis archive dc_28754d0ee511, sha256 96cba06b24080125c462cf1fe20d05148316830805bb075b6b65f78783019e11)

BibTeX

@misc{dc28754d0ee511,
  title = {Scaling Curriculum Learning For Autonomous Driving — arXiv:2608.22549},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.22549},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_28754d0ee511; sha256 96cba06b24080125c462cf1fe20d05148316830805bb075b6b65f78783019e11},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.22549. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Batched simulators for autonomous driving have recently enabled training reinforcement learning (RL) agents at scale, encompassing thousands of traffic scenarios and billions of interactions within a matter of days. Although such high-throughput feeds RL algorithms faster than ever, their sample-efficiency has not kept pace: As the standard training scheme, domain randomization uniformly samples scenarios, thereby consuming a vast number of interactions on cases that contribute little to learning. Curriculum learning offers a remedy by adaptively prioritizing scenarios that matter most to policy improvement. We present CL4AD, the first integration of curriculum learning into batched autonomous driving simulators by framing scenario selection as an unsupervised environment design problem. We introduce utility functions that shape curricula based on success rates and the realism of the agent's behavior, in addition to existing regret-estimation functions. Large-scale experiments in GPUDRIVE demonstrate that curriculum learning achieves a 99% success rate a billion steps earlier than domain randomization, reducing wall-clock time by 77%, and outperforms heuristic curricula with static and dynamic attributes, with only one exception at the largest scale. An ablation under limited compute shows that curriculum learning improves sample efficiency by 67%. We also investigate how utility functions behave at scale, and how prioritized scenarios evolve during training. We release an implementation of CLForAD in GPUDRIVE.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-25 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.22549 — 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 2026-10-18T07:37:52.727Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).