Papers › A Generalist Agent

A Generalist Agent

12 May 2022DeepMind 2022 5arXiv:2205.06175archive 2025-07-28

Scott Reed, Konrad Zolna, Emilio Parisotto, Sergio Gomez Colmenarejo, Alexander Novikov, Gabriel Barth-Maron, Mai Gimenez, Yury Sulsky, Jackie Kay, Jost Tobias Springenberg, Tom Eccles, Jake Bruce, Ali Razavi, Ashley Edwards, Nicolas Heess, Yutian Chen, Raia Hadsell, Oriol Vinyals, Mahyar Bordbar, Nando de Freitas

Inspired by progress in large-scale language modeling, we apply a similar approach towards building a single generalist agent beyond the realm of text outputs. The agent, which we refer to as Gato, works as a multi-modal, multi-task, multi-embodiment generalist policy. The same network with the same weights can play Atari, caption images, chat, stack blocks with a real robot arm and much more, deciding based on its context whether to output text, joint torques, button presses, or other tokens. In this report we describe the model and the data, and document the current capabilities of Gato.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2205.06175")

Code

Syntology Ran 0 of 2 code samples harvested from 1 repository linked to this paper; 2 have no recorded run.

By repository: community (archive-listed): 2 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

LAS1520/Gato-A-Generalist-Agent mentioned on GitHubpytorch report
ManifoldRG/gato-control mentioned on GitHubpytorchGPL-3.0 report
OrigamiDream/gato mentioned on GitHubtfMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

2 samples harvested; 0 ran; 0 honoured the contract we drafted; 2 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2unverified

Licence: 0 of the 2 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from OrigamiDream/gato. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

mu_law_encode OrigamiDream/gato/gato/models/tokenizers.py community (archive-listed) unverified MIT (permissive) · 0615ee0ff9470f2f · report
tokenize_continuous_values OrigamiDream/gato/gato/models/tokenizers.py community (archive-listed) unverified MIT (permissive) · 58f69cafe9ba15e5 · report

Tasks

Language ModelingLanguage ModellingSkill GeneralizationSkill Mastery

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Skill Generalization RGB-Stacking Gato Average 50.2 #1 of 2 Archive leaderboard report
Skill Generalization RGB-Stacking Gato Group 1 24.5 #1 of 2 Archive leaderboard report
Skill Generalization RGB-Stacking Gato Group 2 33 #1 of 2 Archive leaderboard report
Skill Generalization RGB-Stacking Gato Group 3 50.5 #1 of 2 Archive leaderboard report
Skill Generalization RGB-Stacking Gato Group 4 76.5 #1 of 2 Archive leaderboard report
Skill Generalization RGB-Stacking Gato Group 5 66.5 #1 of 2 Archive leaderboard report
Skill Mastery RGB-Stacking Gato Average 75.6 #1 of 2 Archive leaderboard report
Skill Mastery RGB-Stacking Gato Group 1 58 #1 of 2 Archive leaderboard report
Skill Mastery RGB-Stacking Gato Group 2 57.6 #1 of 2 Archive leaderboard report
Skill Mastery RGB-Stacking Gato Group 3 78.5 #1 of 2 Archive leaderboard report
Skill Mastery RGB-Stacking Gato Group 4 89 #1 of 2 Archive leaderboard report
Skill Mastery RGB-Stacking Gato Group 5 95.1 #1 of 2 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections