Papers › Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm

Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm

5 Dec 2017arXiv:1712.01815archive 2025-07-28

David Silver, Thomas Hubert, Julian Schrittwieser, Ioannis Antonoglou, Matthew Lai, Arthur Guez, Marc Lanctot, Laurent SIfre, Dharshan Kumaran, Thore Graepel, Timothy Lillicrap, Karen Simonyan, Demis Hassabis

The game of chess is the most widely-studied domain in the history of artificial intelligence. The strongest programs are based on a combination of sophisticated search techniques, domain-specific adaptations, and handcrafted evaluation functions that have been refined by human experts over several decades. In contrast, the AlphaGo Zero program recently achieved superhuman performance in the game of Go, by tabula rasa reinforcement learning from games of self-play. In this paper, we generalise this approach into a single AlphaZero algorithm that can achieve, tabula rasa, superhuman performance in many challenging domains. Starting from random play, and given no domain knowledge except the game rules, AlphaZero achieved within 24 hours a superhuman level of play in the games of chess and shogi (Japanese chess) as well as Go, and convincingly defeated a world-champion program in each case.

PaperPDFCodeCode 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="1712.01815")

Code

Syntology Ran 13 of 17 code samples harvested from 5 repositories linked to this paper; 4 have no recorded run. Of those that ran: 3 ran · honoured contract; 1 ran · violated contract; 8 ran · our draft was wrong; 1 ran · fixture could not drive it.

By repository: community (archive-listed): 15 samples from 5 repositories, 11 ran; 2 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

62 repositories listed; official and paper-mentioned ones first.

AIRLegend/ChessRL mentioned on GitHubtf report
BertilBraun/ChessBot mentioned on GitHubpytorch report
John-Yu/leelaApplication mentioned on GitHub report
MerceaOtniel/HybridAlpha mentioned on GitHubtf report
MingzhenY/Projects mentioned on GitHub report
Neo-The1/ThinkingTicTacToe mentioned on GitHubtf report
Nkluge-correa/teeny-tiny_castle mentioned on GitHubtfApache-2.0 report
QueensGambit/CrazyAra mentioned on GitHubmxnet report
QueensGambit/CrazyAra-Engine mentioned on GitHub report
Sidus-smg/ataxx-ai mentioned on GitHubpytorch report
Zeta36/chess-alpha-zero mentioned on GitHubtf report
aduerig/burrus mentioned on GitHubtf report
alreadydone/Leela_Phoenix mentioned on GitHubtf report
cjohnchen/changebale mentioned on GitHubtf report
cjohnchen/mirror mentioned on GitHubtf report
cjohnchen/sai mentioned on GitHubtf report
cosmobobak/ttt-ml mentioned on GitHubtf report
fantianwen/laalaz13E mentioned on GitHub report
fantianwen/leela13_training mentioned on GitHubtf report
gcp/leela-zero mentioned on GitHubtf report
glinscott/leela-chess mentioned on GitHubtf report
goodls-cs/leela-zero mentioned on GitHubtf report
gtagency/beta-zero mentioned on GitHub report
helpstonex/crazyara mentioned on GitHubmxnet report
intenseG/BSK mentioned on GitHubtf report
jasonrobwebster/alphazero-clone mentioned on GitHubpytorch report
jonah-chen/alphazero-guerzhoy mentioned on GitHubtf report
jonahs99/baby-zero mentioned on GitHubpytorch report
k-lombard/CS4641_Project mentioned on GitHubtf report
l1t1/lz19 mentioned on GitHubtf report
langorou/vamperouge mentioned on GitHubpytorch report
leela-zero/leela-zero mentioned on GitHubtf report
leelachesszero/lczero mentioned on GitHubtf report
mengyangbai/CchessGo mentioned on GitHub report
pathway/alphaxos mentioned on GitHub report
plkmo/AlphaZero_Connect4 mentioned on GitHubpytorch report
qinwang/leela-zero mentioned on GitHubtf report
ryanp73/ChessAI mentioned on GitHubtf report
sagpant/leela-zero mentioned on GitHubtf report
sai-dev/sai mentioned on GitHub report
saikrishna-1996/deep_pepper_chess mentioned on GitHubpytorch report
samhippie/q-game-agent mentioned on GitHubtf report
samiamkhan/4641Project mentioned on GitHub report
simoll/apo mentioned on GitHubtf report
svikramank/chess-deepRL mentioned on GitHubtf report
tensorflow/minigo mentioned on GitHubtf report
wangml999/chess_zero mentioned on GitHubtf report
wcarvalho/jaxneurorl mentioned on GitHubjax report
zhoujianxing123/minigo_v17 mentioned on GitHubtf 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

17 samples harvested; 13 ran; 3 honoured the contract we drafted; 4 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.

3ran · honoured contract
1ran · violated contract
8ran · our draft was wrong
1ran · fixture could not drive it
4unverified

Licence: 9 of the 17 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 5 repositories linked to this paper, official or community; each sample names its own and says which. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “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.

check_current_planes saikrishna-1996/deep_pepper_chess/game/chess_env.py community (archive-listed) ran · fixture could not drive it no licence file found · pointer only · a58eda7e5b17cc79 · report
get_model_path AIRLegend/ChessRL/src/chessrl/selfplay.py community (archive-listed) ran · our draft was wrong no licence file found · pointer only · 0a0e35f51eb67cba · report
load_from_file michaelnny/alpha_zero/alpha_zero/core/pipeline.py community (archive-listed) ran · our draft was wrong MIT (permissive) · b96683ba59bfac1b · report
montecarloSearch samhippie/q-game-agent/mcts.py community (archive-listed) ran · our draft was wrong MIT (permissive) · fd988c07ec074f4e · report
montecarloSearchImpl samhippie/q-game-agent/mcts.py community (archive-listed) ran · violated contract MIT (permissive) · e7b5cf984bf63ef1 · report
montecarloSearchNN samhippie/q-game-agent/mcts.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 14c1d67b6668d671 · report
playGame samhippie/q-game-agent/agent.py community (archive-listed) ran · our draft was wrong MIT (permissive) · c7d6dbb8bf86e42e · report
round_it michaelnny/alpha_zero/alpha_zero/core/pipeline.py community (archive-listed) ran · honoured contract fingerprinted MIT (permissive) · 9cc703fca50c5430 · report
startprocess MerceaOtniel/HybridAlpha/Coach.py community (archive-listed) ran · our draft was wrong licence not identified · pointer only · 81a1ac33f0025d8d · report
testeval saikrishna-1996/deep_pepper_chess/game/chess_env.py community (archive-listed) ran · honoured contract no licence file found · pointer only · 3ad61b90db37c4ac · report
verifyqueue MerceaOtniel/HybridAlpha/Coach.py community (archive-listed) ran · honoured contract licence not identified · pointer only · d3c9c9ec652d6321 · report
canon_input_planes saikrishna-1996/deep_pepper_chess/game/chess_env.py community (archive-listed) unverified no licence file found · pointer only · d2b40d873baa4080 · report
playWithUser samhippie/q-game-agent/agent.py community (archive-listed) unverified MIT (permissive) · 2ec43855e786d958 · report
testAgainstRandom samhippie/q-game-agent/agent.py community (archive-listed) unverified MIT (permissive) · 9b036e9b6735a5a6 · report
verifyvalues MerceaOtniel/HybridAlpha/Coach.py community (archive-listed) unverified licence not identified · pointer only · 8d30022fe6a8a4ed · report
conv1x1 identical code first harvested elsewhere ran · our draft was wrong licence of this copy not recorded · d9def42110729a85 · report
conv3x3 identical code first harvested elsewhere ran · our draft was wrong licence of this copy not recorded · 160bb14bd76201b4 · report

Tasks

Game of ChessGame of GoGame of ShogiGeneral Reinforcement LearningReinforcement LearningReinforcement Learning (RL)reinforcement-learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Game of Go ELO Ratings AlphaGo Zero ELO Rating 5185 #1 of 1 Archive leaderboard report
Game of Shogi ELO Ratings AlphaZero ELO Rating 4650 #1 of 1 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

Introduced by this paper: AlphaZero

AlphaZeroMulti-Query Attention

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