Greener deep reinforcement learning: analysis of energy and carbon efficiency across Atari benchmarks

Jason Gardner; Ayan Dutta; Swapnoneel Roy; O. Patrick Kreidl; Ladislau Bölöni

doi:10.1007/s10462-026-11520-x

Greener deep reinforcement learning: analysis of energy and carbon efficiency across Atari benchmarks

Jason Gardner
, Ayan Dutta
, Swapnoneel Roy
, O. Patrick Kreidl
, Ladislau Bölöni

School of Computing

University of Central Florida

Producción científica: Article › revisión exhaustiva

Idioma original	English
Número de artículo	148
Publicación	Artificial Intelligence Review
Volumen	59
N.º	6
DOI	https://doi.org/10.1007/s10462-026-11520-x
Estado	Published - jun 2026

ASJC Scopus Subject Areas

Language and Linguistics
Linguistics and Language
Artificial Intelligence

Acceder al documento

10.1007/s10462-026-11520-x

Otros archivos y enlaces

Citar esto

@article{d4bf8a97668c4227abba7dd05925f0d5,

title = "Greener deep reinforcement learning: analysis of energy and carbon efficiency across Atari benchmarks",

keywords = "Deep reinforcement learning, Electricity cost, Energy efficiency, Greenhouse gas emissions",

author = "Jason Gardner and Ayan Dutta and Swapnoneel Roy and \{Patrick Kreidl\}, O. and Ladislau B{\"o}l{\"o}ni",

note = "Publisher Copyright: {\textcopyright} The Author(s) 2026.",

year = "2026",

month = jun,

doi = "10.1007/s10462-026-11520-x",

language = "English",

volume = "59",

number = "6",

}

TY - JOUR

T1 - Greener deep reinforcement learning

T2 - analysis of energy and carbon efficiency across Atari benchmarks

AU - Gardner, Jason

AU - Dutta, Ayan

AU - Roy, Swapnoneel

AU - Patrick Kreidl, O.

AU - Bölöni, Ladislau

N1 - Publisher Copyright: © The Author(s) 2026.

PY - 2026/6

Y1 - 2026/6

KW - Deep reinforcement learning

KW - Electricity cost

KW - Energy efficiency

KW - Greenhouse gas emissions

UR - https://www.scopus.com/pages/publications/105039749246

UR - https://www.scopus.com/pages/publications/105039749246#tab=citedBy

U2 - 10.1007/s10462-026-11520-x

DO - 10.1007/s10462-026-11520-x

M3 - Article

AN - SCOPUS:105039749246

SN - 0269-2821

VL - 59

JO - Artificial Intelligence Review

JF - Artificial Intelligence Review

IS - 6

M1 - 148

ER -