Papers › Evolving simple programs for playing Atari games

Evolving simple programs for playing Atari games

14 Jun 2018arXiv:1806.05695archive 2025-07-28

Dennis G Wilson, Sylvain Cussat-Blanc, Hervé Luga, Julian F. Miller

Cartesian Genetic Programming (CGP) has previously shown capabilities in image processing tasks by evolving programs with a function set specialized for computer vision. A similar approach can be applied to Atari playing. Programs are evolved using mixed type CGP with a function set suited for matrix operations, including image processing, but allowing for controller behavior to emerge. While the programs are relatively small, many controllers are competitive with state of the art methods for the Atari benchmark set and require less training time. By evaluating the programs of the best evolved individuals, simple but effective strategies can be found.

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 9 code samples harvested from 2 repositories linked to this paper: 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 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): 9 samples from 2 repositories, 7 ran (7 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 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

JacobLaney/cgp-tetris mentioned on GitHubMITSyntology: 5 samples, 5 ran (0 instrument-failed) · 0 unverified report
ShuhuaGao/gpFlappyBird mentioned on GitHubMITSyntology: 4 samples, 2 ran (0 instrument-failed) · 2 unverified 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

9 samples harvested: 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 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.

7ran
2unverified

Licence: 0 of the 9 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 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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.

JacobLaney/cgp-tetris community (archive-listed) 5 samples, 5 ran (0 instrument-failed) · 0 unverified
get_column_heights configurations/tetris_heuristic.py ran MIT (permissive) · 5c4c9aa4cbc88e62 · report fixture: signature grid:ndarray/2/int · returned ndarray · level recorded 2026-09-26
get_grid in 24 papers configurations/tetris_heuristic.py ran fingerprinted MIT (permissive) · 42b8b705cb0ccf7d · report fixture: signature pixels:ndarray/3/int · returned ndarray · level recorded 2026-09-26
max2 cgp/functions/comparison.py ran fingerprinted MIT (permissive) · 82cb0a926867b651 · report fixture: signature x:ndarray/1/float, y:ndarray/1/float, p:float/0/float · returned float64 · level recorded 2026-09-26
remove_floating_tile configurations/tetris_heuristic.py ran MIT (permissive) · aeec1a19a777b8d9 · report fixture: signature grid:ndarray/2/int · returned ndarray · level recorded 2026-09-26
run_episode_async cgp/training_environment.py ran MIT (permissive) · d474e08b2934addf · report fixture: signature trainer:SimpleTrainer/0/?, genome:SimpleGenome/0/? · returned dict · level recorded 2026-09-26
ShuhuaGao/gpFlappyBird community (archive-listed) 4 samples, 2 ran (0 instrument-failed) · 2 unverified
evolve cgp.py ran MIT (permissive) · e19e5ccfdc0938b3 · report fixture: signature pop:list/1/Individual, mut_rate:float/0/float, mu:int/0/int, lambda_:int/0/int · returned list · level recorded 2026-09-26
round_expr postprocessing.py ran MIT (permissive) · eb0aac8daa0fc7f1 · report fixture: signature expr:Add/0/?, num_digits:int/0/int · returned Add · level recorded 2026-09-26
protected_div cgp.py unverified MIT (permissive) · 0aaefee9b6b899be · report
simplify postprocessing.py unverified MIT (permissive) · e8359b3bb176b5fa · report

Tasks

Atari Games

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Atari Games Atari 2600 Alien CGP Score 1978 #30 of 49 Archive leaderboard report
Atari Games Atari 2600 Amidar CGP Score 199 #37 of 48 Archive leaderboard report
Atari Games Atari 2600 Assault CGP Score 890.4 #41 of 45 Archive leaderboard report
Atari Games Atari 2600 Asterix CGP Score 1880 #44 of 49 Archive leaderboard report
Atari Games Atari 2600 Asteroids CGP Score 9412 #12 of 43 Archive leaderboard report
Atari Games Atari 2600 Atlantis CGP Score 99240 #39 of 42 Archive leaderboard report
Atari Games Atari 2600 Bank Heist CGP Score 148 #43 of 45 Archive leaderboard report
Atari Games Atari 2600 Battle Zone CGP Score 34200 #21 of 47 Archive leaderboard report
Atari Games Atari 2600 Beam Rider CGP Score 1341.6 #45 of 49 Archive leaderboard report
Atari Games Atari 2600 Berzerk CGP Score 1138 #26 of 39 Archive leaderboard report
Atari Games Atari 2600 Bowling CGP Score 85.8 #14 of 44 Archive leaderboard report
Atari Games Atari 2600 Boxing CGP Score 38.4 #41 of 45 Archive leaderboard report
Atari Games Atari 2600 Breakout CGP Score 13.2 #53 of 58 Archive leaderboard report
Atari Games Atari 2600 Centipede CGP Score 24708 #13 of 45 Archive leaderboard report
Atari Games Atari 2600 Chopper Command CGP Score 3580 #38 of 45 Archive leaderboard report
Atari Games Atari 2600 Crazy Climber CGP Score 12900 #47 of 49 Archive leaderboard report
Atari Games Atari 2600 Defender CGP Score 993010 #1 of 21 Archive leaderboard report
Atari Games Atari 2600 Demon Attack CGP Score 2387 #41 of 46 Archive leaderboard report
Atari Games Atari 2600 Double Dunk CGP Score 2 #19 of 43 Archive leaderboard report
Atari Games Atari 2600 Enduro CGP Score 56.8 #43 of 48 Archive leaderboard report
Atari Games Atari 2600 Fishing Derby CGP Score -51 #43 of 44 Archive leaderboard report
Atari Games Atari 2600 Freeway CGP Score 28.2 #40 of 59 Archive leaderboard report
Atari Games Atari 2600 Frostbite CGP Score 782 #37 of 53 Archive leaderboard report
Atari Games Atari 2600 Gopher CGP Score 1696 #40 of 43 Archive leaderboard report
Atari Games Atari 2600 Gravitar CGP Score 2350 #15 of 53 Archive leaderboard report
Atari Games Atari 2600 HERO CGP Score 2974 #44 of 44 Archive leaderboard report
Atari Games Atari 2600 Ice Hockey CGP Score 4 #13 of 43 Archive leaderboard report
Atari Games Atari 2600 James Bond CGP Score 6130 #13 of 45 Archive leaderboard report
Atari Games Atari 2600 Kangaroo CGP Score 1400 #39 of 47 Archive leaderboard report
Atari Games Atari 2600 Krull CGP Score 9086.8 #23 of 45 Archive leaderboard report
Atari Games Atari 2600 Kung-Fu Master CGP Score 57400 #15 of 43 Archive leaderboard report
Atari Games Atari 2600 Montezuma's Revenge CGP Score 0 #45 of 50 Archive leaderboard report
Atari Games Atari 2600 Ms. Pacman CGP Score 2568 #32 of 47 Archive leaderboard report
Atari Games Atari 2600 Name This Game CGP Score 3696 #40 of 43 Archive leaderboard report
Atari Games Atari 2600 Phoenix CGP Score 7520 #20 of 21 Archive leaderboard report
Atari Games Atari 2600 Pitfall! CGP Score 0 #7 of 23 Archive leaderboard report
Atari Games Atari 2600 Pong CGP Score 20 #29 of 52 Archive leaderboard report
Atari Games Atari 2600 Private Eye CGP Score 12702.2 #10 of 52 Archive leaderboard report
Atari Games Atari 2600 Q*Bert CGP Score 770 #51 of 57 Archive leaderboard report
Atari Games Atari 2600 River Raid CGP Score 2914 #39 of 41 Archive leaderboard report
Atari Games Atari 2600 Road Runner CGP Score 8960 #40 of 44 Archive leaderboard report
Atari Games Atari 2600 Robotank CGP Score 24.2 #35 of 42 Archive leaderboard report
Atari Games Atari 2600 Seaquest CGP Score 724 #48 of 57 Archive leaderboard report
Atari Games Atari 2600 Skiing CGP Score -9011 #9 of 23 Archive leaderboard report
Atari Games Atari 2600 Solaris CGP Score 8324 #9 of 23 Archive leaderboard report
Atari Games Atari 2600 Space Invaders CGP Score 1001 #46 of 55 Archive leaderboard report
Atari Games Atari 2600 Star Gunner CGP Score 2320 #38 of 43 Archive leaderboard report
Atari Games Atari 2600 Tennis CGP Score 0 #25 of 43 Archive leaderboard report
Atari Games Atari 2600 Time Pilot CGP Score 12040 #20 of 44 Archive leaderboard report
Atari Games Atari 2600 Tutankham CGP Score 0 #44 of 44 Archive leaderboard report
Atari Games Atari 2600 Up and Down CGP Score 14524 #34 of 44 Archive leaderboard report
Atari Games Atari 2600 Venture CGP Score 0 #54 of 55 Archive leaderboard report
Atari Games Atari 2600 Video Pinball CGP Score 33752.4 #39 of 42 Archive leaderboard report
Atari Games Atari 2600 Wizard of Wor CGP Score 3820 #34 of 41 Archive leaderboard report
Atari Games Atari 2600 Yars Revenge CGP Score 28838.2 #14 of 17 Archive leaderboard report
Atari Games Atari 2600 Zaxxon CGP Score 2980 #39 of 41 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.

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