Metraipolis › archive › dc_3abfb09a512c

A Geometric Approach to Soft Actor-Critic with Zonotopes for Locomotion Learning — arXiv:2610.12113

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.12113
License (as archived)
CC0-1.0
Archived
2026-10-09T06:03:29.826Z
SHA-256 of the archived text
f83849c0512695992c5f892814a224c4070e6885912347de902a3b850634d939
Stable URL of this page
https://metraipolis.com/documento/dc_3abfb09a512c

How to cite

A Geometric Approach to Soft Actor-Critic with Zonotopes for Locomotion Learning — arXiv:2610.12113 — arXiv (en), https://arxiv.org/abs/2610.12113 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3abfb09a512c (Metraipolis archive dc_3abfb09a512c, sha256 f83849c0512695992c5f892814a224c4070e6885912347de902a3b850634d939)
BibTeX
@misc{dc3abfb09a512c,
  title = {A Geometric Approach to Soft Actor-Critic with Zonotopes for Locomotion Learning — arXiv:2610.12113},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.12113},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3abfb09a512c; sha256 f83849c0512695992c5f892814a224c4070e6885912347de902a3b850634d939},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.12113. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Off-policy actor--critic methods control overestimation bias by taking the minimum of two critics. This uses the same aggregation rule everywhere, regardless of how the critics disagree. We propose \textbf{GeZo-SAC}, which uses auxiliary geometric representations to adapt critic pessimism to the state and action. Alongside its scalar value, each critic predicts a set of generators defining a zonotope. Probing this zonotope along sampled directions provides a geometric width, "subtracted from each critic value as a pessimistic offset, and a measure of disagreement between the two critics, aggregated with log-sum-exp. This disagreement controls how the critics are combined, moving from a width-weighted average toward the usual minimum as disagreement increases. At inference, the deployed policy is an unmodified SAC actor, since the generators are used only on the critic side during this http URL four MuJoCo-v5 locomotion benchmarks and six off-policy baselines, GeZo-SAC achieves the highest mean return on Ant-v5 and Hopper-v5 and remains competitive with other methods on the remaining tasks. Our analysis further shows that GeZo-SAC achieves the lowest average actuator work and action effort per metre among the evaluated methods, while maintaining near-zero measured overestimation frequency across all four environments.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.12113 — 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 2026-10-09T05:47:02.015Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).