Papers › Self-Imitation Learning

Self-Imitation Learning

14 Jun 2018ICML 2018 7arXiv:1806.05635archive 2025-07-28

Junhyuk Oh, Yijie Guo, Satinder Singh, Honglak Lee

This paper proposes Self-Imitation Learning (SIL), a simple off-policy actor-critic algorithm that learns to reproduce the agent's past good decisions. This algorithm is designed to verify our hypothesis that exploiting past good experiences can indirectly drive deep exploration. Our empirical results show that SIL significantly improves advantage actor-critic (A2C) on several hard exploration Atari games and is competitive to the state-of-the-art count-based exploration methods. We also show that SIL improves proximal policy optimization (PPO) on MuJoCo tasks.

PaperPDFConference PDFCodeCode 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

No sample from the archive's official repository (junhyukoh/self-imitation-learning) is linked to this paper; the 6 samples below come from 2 community repositories. Syntology harvested code from junhyukoh/self-imitation-learning for another paper.

junhyukoh/self-imitation-learning: Syntology's graph links these samples to Self-Imitation Learning via Generalized Lower Bound Q-learning (arXiv:2006.07442; that paper's own run record: 16 ran (of which 4 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 3 violated, 4 with no contract checked; 7 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method.

Syntology 6 code samples harvested from 2 repositories linked to this paper: 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 6 samples from 2 repositories, 3 ran (2 with no instrument failure; 1 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.

No sample is linked to this paper from 2 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 3 samples that ran has no recorded date.

junhyukoh/self-imitation-learning officialmentioned in papermentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Self-Imitation Learning via Generalized Lower Bound Q-learning (arXiv:2006.07442; that paper's own run record: 16 ran (of which 4 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 3 violated, 4 with no contract checked; 7 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
SeungeonBaek/continuous-agents-test mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Implicit Distributional Reinforcement Learning (arXiv:2007.06159; that paper's own run record: 4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 4 samples that ran constructed an object rather than computing a result); nothing checks that they implement this paper's method. report
alhabk/SGEE--pytorch mentioned on GitHubpytorchSyntology: 3 samples, 1 ran (1 instrument-failed) · 2 unverified report
rwightman/pytorch-opensim-rl mentioned on GitHubpytorchMITSyntology: 3 samples, 2 ran (0 instrument-failed) · 1 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

6 samples harvested: 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 3 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.

1ran · our draft was wrong
2ran
3unverified

Licence: 3 of the 6 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.

alhabk/SGEE--pytorch community (archive-listed) 3 samples, 1 ran (1 instrument-failed) · 2 unverified
normal_R_V ddpg_sgee.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 1dcc869e62727127 · report fixture: signature R_:list/1/float, current_Q:Tensor/2/float, reward:Tensor/2/float · returned tuple · level recorded, date not recorded
fill_g ddpg_sgee.py unverified no licence file found · pointer only · 83e891466962c711 · report
fill_g sgee_full.py unverified no licence file found · pointer only · a55d844d9f83b2ec · report
rwightman/pytorch-opensim-rl community (archive-listed) 3 samples, 2 ran (0 instrument-failed) · 1 unverified
compute_cov_a in 9 papers algo/kfac.py ran MIT (permissive) · 6aff48ec0d1463e1 · report fixture: signature a:Tensor/4/float, classname:str/0/str, layer_info:tuple/1/tuple, fast_cnn:bool/0/bool · returned Tensor · level recorded 2026-09-25
compute_cov_g in 9 papers algo/kfac.py ran MIT (permissive) · d9fd61d47e236b09 · report fixture: signature g:Tensor/4/float, classname:str/0/str, layer_info:dict/0/?, fast_cnn:bool/0/bool · returned Tensor · level recorded 2026-09-25
project_obs my_prosthetics_env.py unverified MIT (permissive) · 09a10eaced095882 · report

Tasks

Atari GamesImitation LearningMuJoCo

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Atari Games Atari 2600 Alien A2C + SIL Score 2242.2 #29 of 49 Archive leaderboard report
Atari Games Atari 2600 Amidar A2C + SIL Score 1362 #20 of 48 Archive leaderboard report
Atari Games Atari 2600 Assault A2C + SIL Score 1812 #37 of 45 Archive leaderboard report
Atari Games Atari 2600 Asterix A2C + SIL Score 17984.2 #31 of 49 Archive leaderboard report
Atari Games Atari 2600 Asteroids A2C + SIL Score 2259.4 #25 of 43 Archive leaderboard report
Atari Games Atari 2600 Atlantis A2C + SIL Score 3084781.7 #3 of 42 Archive leaderboard report
Atari Games Atari 2600 Bank Heist A2C + SIL Score 1137.8 #19 of 45 Archive leaderboard report
Atari Games Atari 2600 Battle Zone A2C + SIL Score 25075 #32 of 47 Archive leaderboard report
Atari Games Atari 2600 Beam Rider A2C + SIL Score 2366.2 #43 of 49 Archive leaderboard report
Atari Games Atari 2600 Bowling A2C + SIL Score 31.1 #42 of 44 Archive leaderboard report
Atari Games Atari 2600 Boxing A2C + SIL Score 99.6 #14 of 45 Archive leaderboard report
Atari Games Atari 2600 Breakout A2C + SIL Score 452 #22 of 58 Archive leaderboard report
Atari Games Atari 2600 Centipede A2C + SIL Score 7559.5 #26 of 45 Archive leaderboard report
Atari Games Atari 2600 Chopper Command A2C + SIL Score 6710 #24 of 45 Archive leaderboard report
Atari Games Atari 2600 Crazy Climber A2C + SIL Score 130185.8 #24 of 49 Archive leaderboard report
Atari Games Atari 2600 Demon Attack A2C + SIL Score 10140.5 #39 of 46 Archive leaderboard report
Atari Games Atari 2600 Double Dunk A2C + SIL Score 21.5 #12 of 43 Archive leaderboard report
Atari Games Atari 2600 Enduro A2C + SIL Score 1205.1 #29 of 48 Archive leaderboard report
Atari Games Atari 2600 Fishing Derby A2C + SIL Score 55.8 #11 of 44 Archive leaderboard report
Atari Games Atari 2600 Freeway A2C + SIL Score 32.2 #27 of 59 Archive leaderboard report
Atari Games Atari 2600 Frostbite A2C + SIL Score 6289.8 #14 of 53 Archive leaderboard report
Atari Games Atari 2600 Gopher A2C + SIL Score 23304.2 #21 of 43 Archive leaderboard report
Atari Games Atari 2600 Gravitar A2C + SIL Score 1874.2 #18 of 53 Archive leaderboard report
Atari Games Atari 2600 HERO A2C + SIL Score 33156.7 #10 of 44 Archive leaderboard report
Atari Games Atari 2600 Ice Hockey A2C + SIL Score -2.4 #40 of 43 Archive leaderboard report
Atari Games Atari 2600 James Bond A2C + SIL Score 310.8 #42 of 45 Archive leaderboard report
Atari Games Atari 2600 Kangaroo A2C + SIL Score 2888.3 #32 of 47 Archive leaderboard report
Atari Games Atari 2600 Krull A2C + SIL Score 10614.6 #16 of 45 Archive leaderboard report
Atari Games Atari 2600 Kung-Fu Master A2C + SIL Score 34449.2 #26 of 43 Archive leaderboard report
Atari Games Atari 2600 Montezuma's Revenge A2C + SIL Score 1100 #21 of 50 Archive leaderboard report
Atari Games Atari 2600 Ms. Pacman A2C + SIL Score 4025.1 #23 of 47 Archive leaderboard report
Atari Games Atari 2600 Name This Game A2C + SIL Score 14958.2 #17 of 43 Archive leaderboard report
Atari Games Atari 2600 Pong A2C + SIL Score 20.9 #22 of 52 Archive leaderboard report
Atari Games Atari 2600 Private Eye A2C + SIL Score 661.2 #25 of 52 Archive leaderboard report
Atari Games Atari 2600 Q*Bert A2C + SIL Score 104975.6 #6 of 57 Archive leaderboard report
Atari Games Atari 2600 River Raid A2C + SIL Score 14306.1 #22 of 41 Archive leaderboard report
Atari Games Atari 2600 Road Runner A2C + SIL Score 57071.7 #20 of 44 Archive leaderboard report
Atari Games Atari 2600 Robotank A2C + SIL Score 10.5 #39 of 42 Archive leaderboard report
Atari Games Atari 2600 Seaquest A2C + SIL Score 2456.5 #36 of 57 Archive leaderboard report
Atari Games Atari 2600 Space Invaders A2C + SIL Score 2951.7 #27 of 55 Archive leaderboard report
Atari Games Atari 2600 Star Gunner A2C + SIL Score 31309.2 #35 of 43 Archive leaderboard report
Atari Games Atari 2600 Tennis A2C + SIL Score -17.3 #42 of 43 Archive leaderboard report
Atari Games Atari 2600 Time Pilot A2C + SIL Score 10811.7 #22 of 44 Archive leaderboard report
Atari Games Atari 2600 Tutankham A2C + SIL Score 340.5 #8 of 44 Archive leaderboard report
Atari Games Atari 2600 Up and Down A2C + SIL Score 53314.6 #22 of 44 Archive leaderboard report
Atari Games Atari 2600 Venture A2C + SIL Score 0 #53 of 55 Archive leaderboard report
Atari Games Atari 2600 Video Pinball A2C + SIL Score 461522.4 #19 of 42 Archive leaderboard report
Atari Games Atari 2600 Wizard of Wor A2C + SIL Score 7088.3 #26 of 41 Archive leaderboard report
Atari Games Atari 2600 Zaxxon A2C + SIL Score 9164.2 #30 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