Metraipolis › archive › dc_95a8e9fac401
Going Beyond State-Reaching: Learning Abstractions for Intrinsically Motivated Option Discovery — arXiv:2609.36473
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.36473
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T16:22:39.391Z
- SHA-256 of the archived text
b98464c974c8fd9adbf67a81ff9c5125c50e824df3538111e1328c675ef8d60c- Stable URL of this page
https://metraipolis.com/documento/dc_95a8e9fac401
How to cite
Going Beyond State-Reaching: Learning Abstractions for Intrinsically Motivated Option Discovery — arXiv:2609.36473 — arXiv (en), https://arxiv.org/abs/2609.36473 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_95a8e9fac401 (Metraipolis archive dc_95a8e9fac401, sha256 b98464c974c8fd9adbf67a81ff9c5125c50e824df3538111e1328c675ef8d60c)
BibTeX
@misc{dc95a8e9fac401,
title = {Going Beyond State-Reaching: Learning Abstractions for Intrinsically Motivated Option Discovery — arXiv:2609.36473},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.36473},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_95a8e9fac401; sha256 b98464c974c8fd9adbf67a81ff9c5125c50e824df3538111e1328c675ef8d60c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.36473. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Temporal abstraction via options can improve exploration in large environments. However, existing option discovery algorithms find subgoals that target all aspects of the state simultaneously. This state-reaching approach produces options that only apply in narrow regions of the state-space, eventually causing an explosion in the number of options that overwhelms the agent, and impedes progress on its primary task of reward maximization. We introduce an algorithm that instead identifies a small, relevant subset of features for each subgoal, yielding options that generalize broadly and accelerate exploration. Our approach learns abstract, transferrable options and achieves rapid exploration in three sparse-reward, image-based domains, including the Atari game MontezumasRevenge. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.36473 — 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 2026-10-07T15:54:53.503Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).