Metraipolis › archive › dc_89dc14f56534
Geometric Time Score Estimators: Bridging Self-Predictive Representations and Generative Occupancy Models For Reinforcement Learning — arXiv:2610.38901
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.38901
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-01T02:24:55.177Z
- SHA-256 of the archived text
7ae50e5b36c5b71598e8d2aa41d8c2fd1348b2ed219104ba317b785eb130bc6b- Stable URL of this page
https://metraipolis.com/documento/dc_89dc14f56534
How to cite
Geometric Time Score Estimators: Bridging Self-Predictive Representations and Generative Occupancy Models For Reinforcement Learning — arXiv:2610.38901 — arXiv (en), https://arxiv.org/abs/2610.38901 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_89dc14f56534 (Metraipolis archive dc_89dc14f56534, sha256 7ae50e5b36c5b71598e8d2aa41d8c2fd1348b2ed219104ba317b785eb130bc6b)
BibTeX
@misc{dc89dc14f56534,
title = {Geometric Time Score Estimators: Bridging Self-Predictive Representations and Generative Occupancy Models For Reinforcement Learning — arXiv:2610.38901},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.38901},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_89dc14f56534; sha256 7ae50e5b36c5b71598e8d2aa41d8c2fd1348b2ed219104ba317b785eb130bc6b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.38901. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
In reinforcement learning (RL), temporal reasoning is essential for estimating the density of future outcomes under a policy's occupancy measure. While self-predictive representations have been a dominant paradigm for occupancy density estimation, we find that they yield surprisingly poor estimates. On the other hand, generative occupancy models can produce remarkably accurate samples from the occupancy measure. Yet, they cannot easily recover occupancy densities, limiting their use for control despite their expressivity. In this paper, we propose Geometric Time Score Estimators (GTSE), a framework that bridges the two paradigms by learning occupancy density estimators along probability paths. We analyze how GTSE implicitly induces better occupancy estimators through improved representation learning and show how to directly extract self-predictive representations from this framework. Through experiments across several locomotion and manipulation tasks, we show that GTSE improves performance over state-of-the-art methods by $2\times$ to $6\times$ in goal-conditioned RL settings, and that the representations learned using our framework transfer effectively to downstream RL tasks. Website: this https URL 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/2610.38901 — 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 2026-11-01T02:12:44.139Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).