Metraipolis › archive › dc_e4bf92e4a2fd

Revisiting Temporal Regularization for Smooth Control in Deep Reinforcement Learning — arXiv:2610.07910

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.07910
License (as archived): CC0-1.0
Archived: 2026-10-07T11:41:30.196Z
SHA-256 of the archived text: 1c4fa9cb4a886bf41c3e5c74dec3bec49672b7f330c5269fbf07e37794832cd7
Stable URL of this page: https://metraipolis.com/documento/dc_e4bf92e4a2fd

How to cite

Revisiting Temporal Regularization for Smooth Control in Deep Reinforcement Learning — arXiv:2610.07910 — arXiv (en), https://arxiv.org/abs/2610.07910 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e4bf92e4a2fd (Metraipolis archive dc_e4bf92e4a2fd, sha256 1c4fa9cb4a886bf41c3e5c74dec3bec49672b7f330c5269fbf07e37794832cd7)

BibTeX

@misc{dce4bf92e4a2fd,
  title = {Revisiting Temporal Regularization for Smooth Control in Deep Reinforcement Learning — arXiv:2610.07910},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.07910},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e4bf92e4a2fd; sha256 1c4fa9cb4a886bf41c3e5c74dec3bec49672b7f330c5269fbf07e37794832cd7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.07910. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Deep Reinforcement Learning policies can produce nonsmooth action oscillations that hinder deployment on physical robots. Existing architectural and penalty-based approaches seek spatial smoothness by directly reducing sensitivity to changes in state inputs, but their broad constraints can degrade task performance as stronger smoothing is pursued. Temporal regularization instead constrains action differences along observed transitions, but has been considered unable to provide the spatial smoothness needed under observation noise. We revisit this assumption by proving that the temporal penalty bounds the expected action differences between current states sharing a next state, revealing a spatial effect that empirically extends to spatial smoothness. Building on this finding, we propose Conditioning for Action using only Temporal Smoothness (CATS), which combines a temporal penalty with linear ramp-up. We highlight temporal regularization's ability to provide spatial smoothness while better preserving task performance than explicit spatial regularization. Through linear ramp-up, CATS allows the policy to learn rewarding behavior before progressively smoothing its actions, improving return preservation and both temporal and spatial smoothness. Experiments in both simulation and the real world show that CATS substantially reduces action oscillation without degrading task performance, with little computational overhead.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2610.07910 — 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 2026-10-07T11:19:24.800Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).