Metraipolis › archive › dc_8db5fa696c82
Hyperspherical Contrastive Representations Unlock Planning and Exploration — arXiv:2610.20409
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.20409
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T14:20:21.401Z
- SHA-256 of the archived text
e7e25a23af735edd1795afed35f2f7f111d4c6f1f2e6c2957075ccf37e55efbd- Stable URL of this page
https://metraipolis.com/documento/dc_8db5fa696c82
How to cite
Hyperspherical Contrastive Representations Unlock Planning and Exploration — arXiv:2610.20409 — arXiv (en), https://arxiv.org/abs/2610.20409 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8db5fa696c82 (Metraipolis archive dc_8db5fa696c82, sha256 e7e25a23af735edd1795afed35f2f7f111d4c6f1f2e6c2957075ccf37e55efbd)
BibTeX
@misc{dc8db5fa696c82,
title = {Hyperspherical Contrastive Representations Unlock Planning and Exploration — arXiv:2610.20409},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.20409},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8db5fa696c82; sha256 e7e25a23af735edd1795afed35f2f7f111d4c6f1f2e6c2957075ccf37e55efbd},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.20409. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We develop a self-supervised reinforcement learning algorithm that learns to build towers of up to eight cubes from scratch, without prior data, rewards, demonstrations, or pretrained models. Our method, Contrastive Planning via Spherical Linear Interpolation (C-Slerp), uses contrastive representations as reusable building blocks and repeatedly composes them to infer a sequence of intermediate waypoints. Under our hyperspherical parameterization, the learned representations allow intermediate waypoints to be inferred in closed form through spherical linear interpolation, without training a separate high-level policy or performing graph search. Importantly, the representation geometry also tells us how to adjust the number of waypoints based on the difficulty of each goal-reaching problem. Experiments show that our method succeeds on long-horizon navigation and robotic manipulation tasks, including settings where strong baselines fail to achieve a single success. Ablations further show that using a fixed number of waypoints substantially degrades performance, highlighting the importance of adapting the plan to task difficulty. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.20409 — 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 2026-10-15T13:53:35.745Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).