Papers › Scaling Scaling Laws with Board Games

Scaling Scaling Laws with Board Games

7 Apr 2021arXiv:2104.03113archive 2025-07-28

Andy L. Jones

The largest experiments in machine learning now require resources far beyond the budget of all but a few institutions. Fortunately, it has recently been shown that the results of these huge experiments can often be extrapolated from the results of a sequence of far smaller, cheaper experiments. In this work, we show that not only can the extrapolation be done based on the size of the model, but on the size of the problem as well. By conducting a sequence of experiments using AlphaZero and Hex, we show that the performance achievable with a fixed amount of compute degrades predictably as the game gets larger and harder. Along with our main result, we further show that the test-time and train-time compute available to an agent can be traded off while maintaining performance.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 20 code samples harvested from 1 repository linked to this paper: 13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 20 samples from 1 repository, 13 ran (13 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

andyljones/boardlaw mentioned on GitHubpytorchMITSyntology: 20 samples, 13 ran (0 instrument-failed) · 7 unverified report
fabricerosay/AlphaGPU mentioned on GitHubGPL-3.0Syntology: not harvested 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

20 samples harvested: 13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

13ran
7unverified

Licence: 0 of the 20 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 andyljones/boardlaw. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

andyljones/boardlaw community (archive-listed) 20 samples, 13 ran (0 instrument-failed) · 7 unverified
as_sgf boardlaw/mohex.py ran MIT (permissive) · fc7d2bf32c4f8c81 · report fixture: signature obs:Tensor/3/float, seat:int/0/int · returned str · level recorded 2026-09-24
combine_actions boardlaw/analysis.py ran MIT (permissive) · a945e25cb4a786b7 · report fixture: signature decisions:dict/0/?, masks:dict/0/? · returned Tensor · level recorded 2026-09-24
configfile boardlaw/mohex.py ran MIT (permissive) · c5bfe30be69a2cb9 · report fixture: signature max_games:int/0/int, max_memory:float/0/float, presearch:bool/0/bool, max_time:float/0/float, max_nodes:int/0/int, solver:bool/0/bool, extras:list/1/str · returned str · level recorded 2026-09-24
expand in 29 papers boardlaw/analysis.py ran fingerprinted MIT (permissive) · c1f40ed24b504f3a · report fixture: signature exemplar:Tensor/2/float, n_envs:int/0/int · returned Tensor · level recorded 2026-09-24
flops_savepoints boardlaw/storage.py ran MIT (permissive) · 6991e3c1ba7a74a3 · report fixture: signature boardsize:int/0/int, n_snapshots:int/0/int, upper:NoneType/0/? · returned ndarray · level recorded 2026-09-24
mix in 6 papers boardlaw/learning.py ran MIT (permissive) · 4012a2148ebeacb0 · report fixture: signature worlds:WorldsStandIn/0/?, T:int/0/int · returned WorldsStandIn · level recorded 2026-09-24
rel_entropy boardlaw/learning.py ran fingerprinted MIT (permissive) · 3f45524f680d14f5 · report fixture: signature logits:Tensor/2/float · returned tuple · level recorded 2026-09-24
scatter_values boardlaw/heads.py ran fingerprinted MIT (permissive) · 367074d89cc98d11 · report fixture: signature v:Tensor/2/float, seats:Tensor/2/float · returned Tensor · level recorded 2026-09-24
solve in 25 papers boardlaw/elos.py ran MIT (permissive) · 36de63ed4f7ee176 · report fixture: signature wins:DataFrame/0/?, games:DataFrame/0/?, prior:int/0/int · returned Series · level recorded 2026-09-24
symmetrize in 19 papers boardlaw/elos.py ran MIT (permissive) · 834bf0198db420c4 · report fixture: signature trials:DataFrame/0/? · returned tuple · level recorded 2026-09-24
time_savepoints boardlaw/storage.py ran MIT (permissive) · 2e13a5fddcf146ef · report fixture: signature boardsize:int/0/int, n_snapshots:int/0/int · returned ndarray · level recorded 2026-09-24
to_notation boardlaw/mohex.py ran MIT (permissive) · 4b902338baafdbbc · report fixture: signature subscript:tuple/1/int · returned str · level recorded 2026-09-24
uniform_logits boardlaw/validation.py ran fingerprinted MIT (permissive) · d9741f5b1322e325 · report fixture: signature valid:Tensor/2/int · returned Tensor · level recorded 2026-09-24
elo_errors boardlaw/elos.py unverified MIT (permissive) · a642ea35e15e247c · report
flops_per_sample boardlaw/storage.py unverified MIT (permissive) · e2bd1b373ebc52bb · report
intake boardlaw/heads.py unverified MIT (permissive) · 0ed1dad28421148d · report
load in 392 papers boardlaw/cuda.py unverified MIT (permissive) · af40ded331a17cf3 · report
load_cpu boardlaw/cuda.py unverified MIT (permissive) · 4d4db23102df95b8 · report
load_cuda boardlaw/cuda.py unverified MIT (permissive) · f665e38eed24b93d · report
output boardlaw/heads.py unverified MIT (permissive) · ffd08286e32eb008 · report

Tasks

Board Games

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AlphaZero

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