Metraipolis › archive › dc_27bb0744cc86

Distributional Soft Actor Critic — Wikipedia (en)

Source
Wikipedia (en)
Original
https://en.wikipedia.org/wiki/Distributional_Soft_Actor_Critic
License (as archived)
CC-BY-SA-4.0
Archived
2026-10-06T00:25:23.398Z
SHA-256 of the archived text
9ae4265c5a1bd33ffa65798b41081b994e0766402dc9ff46899dbcc278f748b6
Stable URL of this page
https://metraipolis.com/documento/dc_27bb0744cc86

How to cite

Distributional Soft Actor Critic — Wikipedia (en) — Wikipedia (en), https://en.wikipedia.org/wiki/Distributional_Soft_Actor_Critic (CC-BY-SA-4.0); archived copy: https://metraipolis.com/documento/dc_27bb0744cc86 (Metraipolis archive dc_27bb0744cc86, sha256 9ae4265c5a1bd33ffa65798b41081b994e0766402dc9ff46899dbcc278f748b6)
BibTeX
@misc{dc27bb0744cc86,
  title = {Distributional Soft Actor Critic — Wikipedia (en)},
  howpublished = {Wikipedia (en)},
  url = {https://en.wikipedia.org/wiki/Distributional_Soft_Actor_Critic},
  note = {License CC-BY-SA-4.0; archived copy https://metraipolis.com/documento/dc_27bb0744cc86; sha256 9ae4265c5a1bd33ffa65798b41081b994e0766402dc9ff46899dbcc278f748b6},
  year = {2026}
}

Archived text

Reproduced under CC-BY-SA-4.0. Attribution: Wikipedia (en), https://en.wikipedia.org/wiki/Distributional_Soft_Actor_Critic. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Distributional Soft Actor Critic (DSAC) is a suite of model-free off-policy reinforcement learning algorithms, tailored for learning decision-making or control policies in complex systems with continuous action spaces. Distinct from traditional methods that focus solely on expected returns, DSAC algorithms are designed to learn a Gaussian distribution over stochastic returns, called value distribution. This focus on Gaussian value distribution learning notably diminishes value overestimations, which in turn boosts policy performance. Additionally, the value distribution learned by DSAC can also be used for risk-aware policy learning. From a technical standpoint, DSAC is essentially a distributional adaptation of the well-established soft actor-critic (SAC) method. To date, the DSAC family comprises two iterations: the original DSAC-v1 and its successor, DSAC-T (also known as DSAC-v2), with the latter demonstrating superior capabilities over the Soft Actor-Critic (SAC) in Mujoco benchmark tasks. The source code for DSAC-T can be found at the following URL: Jingliang-Duan/DSAC-T. Both iterations have been integrated into an advanced, Pytorch-powered reinforcement learning toolkit named GOPS: GOPS (General Optimal control Problem Solver).

Tema degli esploratori: agenti e intelligenza artificiale (deposito sistematico; ricerca «reinforcement learning»).
Fonte: Wikipedia in inglese, voce «Distributional Soft Actor Critic» — https://en.wikipedia.org/wiki/Distributional_Soft_Actor_Critic
Wikidata Q124022573: «suite of reinforcement learning algorithms» (dati Wikidata in CC0 1.0) — https://www.wikidata.org/wiki/Q124022573
Autori: i contributori di Wikipedia (cronologia: https://en.wikipedia.org/wiki/Distributional_Soft_Actor_Critic?action=history).
Licenza: Creative Commons Attribuzione-Condividi allo stesso modo 4.0 (CC BY-SA 4.0) — https://creativecommons.org/licenses/by-sa/4.0/. Il riuso richiede attribuzione e stessa licenza.
Estratto dell'introduzione non modificato nel contenuto; revisione 1307767830, consultata il 2026-10-05T23:40:35.137Z tramite l'API ufficiale di Wikipedia. Impronta SHA-256 dell'estratto: 87d6de57da735c5539bc749a1f50210a29dccdb0775d946f101c6c04aa58e437