Metraipolis › archive › dc_2be959537da0
Active Curriculum Refinement for Reinforcement Learning — arXiv:2608.26469
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.26469
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T16:09:27.085Z
- SHA-256 of the archived text
8ae5a41a4f3e78b4e20094094bf95eaab5dd24bafe2ad542e9ddb4266cf67007- Stable URL of this page
https://metraipolis.com/documento/dc_2be959537da0
How to cite
Active Curriculum Refinement for Reinforcement Learning — arXiv:2608.26469 — arXiv (en), https://arxiv.org/abs/2608.26469 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2be959537da0 (Metraipolis archive dc_2be959537da0, sha256 8ae5a41a4f3e78b4e20094094bf95eaab5dd24bafe2ad542e9ddb4266cf67007)
BibTeX
@misc{dc2be959537da0,
title = {Active Curriculum Refinement for Reinforcement Learning — arXiv:2608.26469},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.26469},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2be959537da0; sha256 8ae5a41a4f3e78b4e20094094bf95eaab5dd24bafe2ad542e9ddb4266cf67007},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.26469. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
In many reinforcement learning (RL) domains, environments are connected by prerequisite relations, such as difficulty-increasing edits or parameter increments, which induce a directed acyclic curriculum graph (DAG). Although this structure is often exploited only implicitly, explicitly modeling it can improve training. We introduce PATH, a curriculum-learning framework that performs active learning over the curriculum graph. PATH first expands coverage by sampling diverse curriculum paths and then reallocates training toward regions that remain unmastered. Experiments across diverse environments show that PATH explicitly leverages the graph structure to achieve strong robustness and generalization. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-28 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2608.26469 — 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 2026-10-17T15:34:49.898Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).