Paper Citation Record · LEDGER

Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks

As of 19 August 2026, this Paper Citation Record lists 41 of 41 outbound references and 1 inbound Pith citation observation for arXiv:2509.05273.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2509.05273 v1

Coverage vector

measured 41 of 41 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T16:30:01.098178Z

measured 42 of 42 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-04T12:54:39.977138Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: cited_works

Reference resolution

41 of 41 outbound references displayed

verified exact1
verified fuzzy19
unresolved20
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 161420a3-d065-4b67-88b2-b955a61e42b1 · outbound

This paper cites Monthly energy review december 2024,.

Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks Monthly energy review december 2024,

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:30:01.980697Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 66b2c8e6-20f9-438f-9d49-c17943831d49 · outbound

This paper cites The real climate and transformative impact of ICT: A critique of estimates, trends, and regulations,.

Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks The real climate and transformative impact of ICT: A critique of estimates, trends, and regulations,

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:30:01.961388Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 85317a72-580a-4210-b77a-44e9a829c126 · outbound

This paper cites Powering intelligence: Analyzing artificial intelligence and data center energy consumption,.

Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks Powering intelligence: Analyzing artificial intelligence and data center energy consumption,

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-15T16:30:00.912804Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1ac4900-a525-4871-8ea4-328643460e04 · outbound

This paper cites llama-models/models/llama3 1/MODEL CARD.md at main - meta-llama/llama-models,.

Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks llama-models/models/llama3 1/MODEL CARD.md at main - meta-llama/llama-models,

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:30:01.944034Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation e6217dc0-60ce-4ca2-afda-8630aefebc55 · outbound

This paper cites llama-models/models/llama3 3/MODEL CARD.md at main - meta-llama/llama-models,.

Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks llama-models/models/llama3 3/MODEL CARD.md at main - meta-llama/llama-models,

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:30:01.925888Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation ba1c7a40-002f-4280-81b9-46e92353c42c · outbound

This paper cites Estimating the Carbon Footprint of BLOOM, a 176B Parameter Language Model.

Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks Estimating the Carbon Footprint of BLOOM, a 176B Parameter Language Model

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-15T16:30:00.927799Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08a81d08-1310-4ca5-9d2f-081973aa8748 · outbound

This paper cites Google 2024 sustainability report,.

Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks Google 2024 sustainability report,

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:30:01.907984Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 38f0d3a1-21c2-4117-90c8-ce7275ef4844 · outbound

This paper cites Ai index report — stanford human-centered artificial intelligence.

Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks Ai index report — stanford human-centered artificial intelligence

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:30:01.868937Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation e011fd23-89b5-40ca-a144-ffa46a80bbd1 · outbound

This paper cites A single modern AI GPU consumes up to 3.7 MWh of power per year — GPUs sold last year alone consumed more power than 1.3 million homes — tomshardware.com,.

Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks A single modern AI GPU consumes up to 3.7 MWh of power per year — GPUs sold last year alone consumed more power than 1.3 million homes — tomshardware.com,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:30:01.848837Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 1c60c831-65dd-4c43-9b48-a3a97977512c · outbound

This paper cites Energy and policy con- siderations for modern deep learning research,.

Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks Energy and policy con- siderations for modern deep learning research,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:30:01.827676Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 5759d967-1937-405e-854a-b082a2dcd36d · outbound

This paper cites The carbon footprint of machine learning training will plateau, then shrink,.

Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks The carbon footprint of machine learning training will plateau, then shrink,

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-15T16:30:00.957102Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation abf5fdf8-0cd8-4bc8-9f79-ebb7f946e486 · outbound

This paper cites Green ai,.

Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks Green ai,

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-15T16:30:00.962007Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a1d98db-c2ef-4600-a296-8b7b29acfb4b · outbound

This paper cites Sustainable ai: Environmental implications, challenges and opportunities,.

Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks Sustainable ai: Environmental implications, challenges and opportunities,

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-15T16:30:00.966662Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3c4b086-d606-4ad3-b6b8-f652e36736b9 · outbound

This paper cites Deep reinforcement learning that matters,.

Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks Deep reinforcement learning that matters,

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-15T16:30:00.971647Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3cc5cde8-e828-4b8c-a869-f4ff5772a7b0 · outbound

This paper cites Implementation Matters in Deep Policy Gradients: A Case Study on PPO and TRPO.

Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks Implementation Matters in Deep Policy Gradients: A Case Study on PPO and TRPO

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-15T16:30:00.976208Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5bb043ef-4271-4b76-afb1-dafe3ef4141e · outbound

This paper cites Reproducibility of Benchmarked Deep Reinforcement Learning Tasks for Continuous Control.

Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks Reproducibility of Benchmarked Deep Reinforcement Learning Tasks for Continuous Control

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-15T16:30:00.981104Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c5d4941-910f-4d4f-987a-e5d5afdfea08 · outbound

This paper cites Towards the systematic reporting of the energy and carbon footprints of machine learning,.

Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks Towards the systematic reporting of the energy and carbon footprints of machine learning,

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-15T16:30:00.986260Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad4ee1dc-c20b-4e71-8612-edd7f2a369d6 · outbound

This paper cites Human-level control through deep reinforcement learning,.

Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks Human-level control through deep reinforcement learning,

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-15T16:30:00.991146Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92441e72-15ac-4b71-93a3-87b3eff1b203 · outbound

This paper cites Distributional Reinforcement Learning with Quantile Regression.

Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks Distributional Reinforcement Learning with Quantile Regression

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-15T16:30:00.995891Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 221bd5f0-7364-4e3e-96d3-4b625299d41e · outbound

This paper cites Asynchronous methods for deep reinforcement learning,.

Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks Asynchronous methods for deep reinforcement learning,

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-15T16:30:01.001106Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2f1efab-26a2-4436-ac46-39e462839132 · outbound

This paper cites Proximal Policy Optimization Algorithms.

Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks Proximal Policy Optimization Algorithms

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-15T16:30:01.005707Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c406e096-6109-4a6b-ba30-5f6d536f7f40 · outbound

This paper cites Trust region policy optimization,.

Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks Trust region policy optimization,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:30:01.728893Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation a597a9e5-4c22-4670-9346-1975e3cc2596 · outbound

This paper cites Simple random search of static linear policies is competitive for reinforcement learning,.

Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks Simple random search of static linear policies is competitive for reinforcement learning,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:30:01.712116Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation c0ecb4d1-f142-4ec6-995d-9332cc7273d9 · outbound

This paper cites Impala: Scalable dis- tributed deep-rl with importance weighted actor-learner architectures,.

Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks Impala: Scalable dis- tributed deep-rl with importance weighted actor-learner architectures,

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-15T16:30:01.020335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3aa9e5d2-c41b-4eb8-a5ab-83ba0a4718e5 · outbound

This paper cites Phasic policy gradient,.

Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks Phasic policy gradient,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:30:01.674484Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 200fd7e1-0ec5-4cf4-98ce-5aaa7990c6d4 · outbound

This paper cites Deep Reinforcement Learning with Double Q-learning.

Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks Deep Reinforcement Learning with Double Q-learning

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-15T16:30:01.030143Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b691eeb-ba93-4846-b0bc-fe55b14e3dd3 · outbound

This paper cites Gdm-net: Gas distribution mapping with a mobile robot using deep reinforcement learning and gaussian process regression,.

Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks Gdm-net: Gas distribution mapping with a mobile robot using deep reinforcement learning and gaussian process regression,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:30:01.649156Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 4f8a6515-c435-4a8b-8ae4-803157881b40 · outbound

This paper cites Deep reinforcement learning for autonomous driving: A survey,.

Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks Deep reinforcement learning for autonomous driving: A survey,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:30:01.628654Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 55370e6c-bd8a-46ee-9a2b-992c74c6813c · outbound

This paper cites Stable-Baselines3: Reliable reinforcement learning implementations,.

Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks Stable-Baselines3: Reliable reinforcement learning implementations,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:30:01.606586Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 36b1d9b1-cb93-4452-9a14-558ba644d07a · outbound

This paper cites Gymnasium: A Standard Interface for Reinforcement Learning Environments.

Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks Gymnasium: A Standard Interface for Reinforcement Learning Environments

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-15T16:30:01.053190Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1938f371-8da7-4d9c-b246-c8b43c5b97e3 · outbound

This paper cites TensorFlow: Large-scale machine learning on heterogeneous systems,.

Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks TensorFlow: Large-scale machine learning on heterogeneous systems,

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-15T16:30:01.059569Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab9a3c30-435a-409a-93bc-d1e377c99de3 · outbound

This paper cites Scalable parallel programming with cuda,.

Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks Scalable parallel programming with cuda,

Reference 32

Resolution: verified exact; doi, observed 2026-08-15T16:30:01.167180Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 2604ef47-5794-4f12-94c1-f174d30f9e28 · outbound

This paper cites mlco2/codecarbon: v2.4.1,.

Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks mlco2/codecarbon: v2.4.1,

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-15T16:30:01.069299Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb25df81-234e-4af4-a5ac-4a3227e41318 · outbound

This paper cites United states of america 2024 carbon intensity data,.

Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks United states of america 2024 carbon intensity data,

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:30:01.560025Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 12ffead1-573a-4774-9230-d01d1315b83d · outbound

This paper cites The arcade learning environment: An evaluation platform for general agents,.

Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks The arcade learning environment: An evaluation platform for general agents,

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:30:01.541392Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 14037c70-2128-4f5e-972d-c21a661e70a4 · outbound

This paper cites Rl algorithms — stable baselines 2.10.3a0 documentation.

Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks Rl algorithms — stable baselines 2.10.3a0 documentation

Reference 36

Resolution: malformed identifier; raw_fallback, observed 2026-08-15T16:30:01.520895Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 12c1c2ad-65ee-41ff-bd52-0962ceddd894 · outbound

This paper cites Average energy prices for the united states, regions, census divisions, and selected metropolitan areas : Midwest information office : U.s. bureau of labor statistics.

Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks Average energy prices for the united states, regions, census divisions, and selected metropolitan areas : Midwest information office : U.s. bureau of labor statistics

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:30:01.503250Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation c6dfafc5-3905-4f00-8ea4-53a3c8465cb1 · outbound

This paper cites Rates — my account — local.

Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks Rates — my account — local

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:30:01.484145Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation e19676d9-c6b0-406f-bc25-1351da0e7668 · outbound

This paper cites Available: https://doi.org/10.1613/jair.3912.

Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks Available: https://doi.org/10.1613/jair.3912

Reference 2013

Resolution: unresolved; no resolver link, observed 2026-08-15T16:30:01.083775Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 63ef888d-98d6-46b3-a70d-81091ccb2da6 · outbound

This paper cites Available: https://doi.org/10.1016/j.patter.2021.100340.

Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks Available: https://doi.org/10.1016/j.patter.2021.100340

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-15T16:30:00.908129Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 207ad6ac-fd2c-4db6-a58d-05e76d46216a · outbound

This paper cites Available: https://sustainability.google/reports/.

Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks Available: https://sustainability.google/reports/

Reference 2024

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:30:01.888458Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Pith citing papers

Observation 4e397cfd-af6e-4aaf-8632-5bc7c902f2af · inbound

Octax: Accelerated CHIP-8 Arcade Environments for Reinforcement Learning in JAX cites this paper.

Octax: Accelerated CHIP-8 Arcade Environments for Reinforcement Learning in JAX Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-04T12:54:39.977138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.