Papers › Implicit Quantile Networks for Distributional Reinforcement Learning

Implicit Quantile Networks for Distributional Reinforcement Learning

14 Jun 2018ICML 2018 7arXiv:1806.06923archive 2025-07-28

Will Dabney, Georg Ostrovski, David Silver, Rémi Munos

In this work, we build on recent advances in distributional reinforcement learning to give a generally applicable, flexible, and state-of-the-art distributional variant of DQN. We achieve this by using quantile regression to approximate the full quantile function for the state-action return distribution. By reparameterizing a distribution over the sample space, this yields an implicitly defined return distribution and gives rise to a large class of risk-sensitive policies. We demonstrate improved performance on the 57 Atari 2600 games in the ALE, and use our algorithm's implicitly defined distributions to study the effects of risk-sensitive policies in Atari games.

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

Syntology 2 code samples harvested from 1 repository linked to this paper: 2 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; 0 where Syntology's instrument failed) · 0 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): 2 samples from 1 repository, 2 ran (2 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.

No sample is linked to this paper from 9 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-24 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

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

ACampero/dopamine mentioned on GitHubtfApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Dopamine: A Research Framework for Deep Reinforcement Learning (arXiv:1812.06110; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 13 unverified); nothing checks that they implement this paper's method. report
Abdelhamid-bouzid/Distributional-RL mentioned on GitHubpytorchSyntology: not harvested report
BY571/IQN mentioned on GitHubpytorchMITSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
GoingMyWay/dopamine_reward_decomposition mentioned on GitHubtfApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Dopamine: A Research Framework for Deep Reinforcement Learning (arXiv:1812.06110; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 13 unverified); nothing checks that they implement this paper's method. report
KatyNTsachi/Hierarchical-RL mentioned on GitHubtfApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Dopamine: A Research Framework for Deep Reinforcement Learning (arXiv:1812.06110; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 13 unverified); nothing checks that they implement this paper's method. report
Kchu/DeepRL_CK mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to QUOTA: The Quantile Option Architecture for Reinforcement Learning (arXiv:1811.02073; that paper's own run record: 2 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; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
V0LsTeR/DQN_heap mentioned on GitHubtfApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Dopamine: A Research Framework for Deep Reinforcement Learning (arXiv:1812.06110; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 13 unverified); nothing checks that they implement this paper's method. report
V0LsTeR/dopamine_prioritized_buffer mentioned on GitHubtfApache-2.0Syntology: not harvested report
chainer/chainerrl mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ChainerRL: A Deep Reinforcement Learning Library (arXiv:1912.03905; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
ku2482/fqf-iqn-qrdqn.pytorch mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Fully Parameterized Quantile Function for Distributional Reinforcement Learning (arXiv:1911.02140; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
ku2482/rljax mentioned on GitHubjaxMITSyntology: not harvested report
marload/DistRL-TensorFlow2 mentioned on GitHubtfApache-2.0Syntology: not harvested report
marload/dist-rl-tf2 mentioned on GitHubtfApache-2.0Syntology: not harvested report
pihey1995/DistributionalRL mentioned on GitHubpytorchSyntology: not harvested report
robinzixuan/IQN_Agent mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Fully Parameterized Quantile Function for Distributional Reinforcement Learning (arXiv:1911.02140; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
sjYoondeltar/IQN_example mentioned on GitHubtfSyntology: not harvested report
sjYoondeltar/myRL_example mentioned on GitHubtfSyntology: not harvested report
SeungeonBaek/discrete-agents-test tfMITSyntology: not harvested report
opendilab/DI-engine pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Hindsight Experience Replay (arXiv:1707.01495; that paper's own run record: 16 ran (of which 10 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified), Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context (arXiv:1901.02860; that paper's own run record: 67 ran (of which 37 constructed an object rather than computing a result; 49 with no instrument failure: 4 honoured, 1 violated, 44 with no contract checked; 18 where Syntology's instrument failed) · 76 unverified), Decision Transformer: Reinforcement Learning via Sequence Modeling (arXiv:2106.01345; that paper's own run record: 17 ran (of which 10 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 5 where Syntology's instrument failed) · 9 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. 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

2 samples harvested: 2 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; 0 where Syntology's instrument failed) · 0 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.

2ran

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 BY571/IQN. “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.

BY571/IQN community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
calculate_huber_loss in 5 papers agent.py ran fingerprinted MIT (permissive) · 8563b54f28d9f9c6 · report fixture: signature td_errors:Tensor/2/float, k:float/0/float · returned Tensor · level recorded 2026-09-26
make_env in 50 papers wrapper.py ran MIT (permissive) · 06fc02646fefa30a · report fixture: signature env_name:str/0/str · returned ScaledFloatFrame · level recorded 2026-09-24

Tasks

Atari GamesDistributional Reinforcement LearningReinforcement LearningReinforcement Learning (RL)quantile regressionregressionreinforcement-learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Atari Games Atari 2600 Alien IQN Score 7022 #13 of 49 Archive leaderboard report
Atari Games Atari 2600 Amidar IQN Score 2946 #7 of 48 Archive leaderboard report
Atari Games Atari 2600 Assault IQN Score 29091 #7 of 45 Archive leaderboard report
Atari Games Atari 2600 Asterix IQN Score 342016 #13 of 49 Archive leaderboard report
Atari Games Atari 2600 Asteroids IQN Score 2898 #20 of 43 Archive leaderboard report
Atari Games Atari 2600 Atlantis IQN Score 978200 #13 of 42 Archive leaderboard report
Atari Games Atari 2600 Bank Heist IQN Score 1416 #7 of 45 Archive leaderboard report
Atari Games Atari 2600 Battle Zone IQN Score 42244 #13 of 47 Archive leaderboard report
Atari Games Atari 2600 Beam Rider IQN Score 42776 #9 of 49 Archive leaderboard report
Atari Games Atari 2600 Berzerk IQN Score 1053 #27 of 39 Archive leaderboard report
Atari Games Atari 2600 Bowling IQN Score 86.5 #13 of 44 Archive leaderboard report
Atari Games Atari 2600 Boxing IQN Score 99.8 #13 of 45 Archive leaderboard report
Atari Games Atari 2600 Breakout IQN Score 734 #15 of 58 Archive leaderboard report
Atari Games Atari 2600 Centipede IQN Score 11561 #17 of 45 Archive leaderboard report
Atari Games Atari 2600 Chopper Command IQN Score 16836 #13 of 45 Archive leaderboard report
Atari Games Atari 2600 Crazy Climber IQN Score 179082 #11 of 49 Archive leaderboard report
Atari Games Atari 2600 Defender IQN Score 53537 #13 of 21 Archive leaderboard report
Atari Games Atari 2600 Demon Attack IQN Score 128580 #12 of 46 Archive leaderboard report
Atari Games Atari 2600 Double Dunk IQN Score 5.6 #16 of 43 Archive leaderboard report
Atari Games Atari 2600 Enduro IQN Score 2359 #9 of 48 Archive leaderboard report
Atari Games Atari 2600 Fishing Derby IQN Score 33.8 #22 of 44 Archive leaderboard report
Atari Games Atari 2600 Freeway IQN Score 34 #2 of 59 Archive leaderboard report
Atari Games Atari 2600 Frostbite IQN Score 4324 #19 of 53 Archive leaderboard report
Atari Games Atari 2600 Gopher IQN Score 118365 #7 of 43 Archive leaderboard report
Atari Games Atari 2600 Gravitar IQN Score 911 #24 of 53 Archive leaderboard report
Atari Games Atari 2600 HERO IQN Score 28386 #17 of 44 Archive leaderboard report
Atari Games Atari 2600 Ice Hockey IQN Score 0.2 #19 of 43 Archive leaderboard report
Atari Games Atari 2600 James Bond IQN Score 35108 #8 of 45 Archive leaderboard report
Atari Games Atari 2600 Kangaroo IQN Score 15487 #4 of 47 Archive leaderboard report
Atari Games Atari 2600 Krull IQN Score 10707 #15 of 45 Archive leaderboard report
Atari Games Atari 2600 Kung-Fu Master IQN Score 73512 #13 of 43 Archive leaderboard report
Atari Games Atari 2600 Montezuma's Revenge IQN Score 0 #42 of 50 Archive leaderboard report
Atari Games Atari 2600 Ms. Pacman IQN Score 6349 #14 of 47 Archive leaderboard report
Atari Games Atari 2600 Name This Game IQN Score 22682 #9 of 43 Archive leaderboard report
Atari Games Atari 2600 Phoenix IQN Score 56599 #14 of 21 Archive leaderboard report
Atari Games Atari 2600 Pitfall! IQN Score 0 #4 of 23 Archive leaderboard report
Atari Games Atari 2600 Pong IQN Score 21 #3 of 52 Archive leaderboard report
Atari Games Atari 2600 Private Eye IQN Score 200 #37 of 52 Archive leaderboard report
Atari Games Atari 2600 Q*Bert IQN Score 25750 #16 of 57 Archive leaderboard report
Atari Games Atari 2600 River Raid IQN Score 17765 #13 of 41 Archive leaderboard report
Atari Games Atari 2600 Road Runner IQN Score 57900 #17 of 44 Archive leaderboard report
Atari Games Atari 2600 Robotank IQN Score 62.5 #21 of 42 Archive leaderboard report
Atari Games Atari 2600 Seaquest IQN Score 30140 #13 of 57 Archive leaderboard report
Atari Games Atari 2600 Skiing IQN Score -9289 #3 of 23 Archive leaderboard report
Atari Games Atari 2600 Solaris IQN Score 8007 #10 of 23 Archive leaderboard report
Atari Games Atari 2600 Space Invaders IQN Score 28888 #11 of 55 Archive leaderboard report
Atari Games Atari 2600 Star Gunner IQN Score 74677 #21 of 43 Archive leaderboard report
Atari Games Atari 2600 Surround IQN Score 9.4 #6 of 15 Archive leaderboard report
Atari Games Atari 2600 Tennis IQN Score 23.6 #6 of 43 Archive leaderboard report
Atari Games Atari 2600 Time Pilot IQN Score 12236 #18 of 44 Archive leaderboard report
Atari Games Atari 2600 Tutankham IQN Score 293 #10 of 44 Archive leaderboard report
Atari Games Atari 2600 Up and Down IQN Score 88148 #15 of 44 Archive leaderboard report
Atari Games Atari 2600 Venture IQN Score 1318 #15 of 55 Archive leaderboard report
Atari Games Atari 2600 Video Pinball IQN Score 698045 #11 of 42 Archive leaderboard report
Atari Games Atari 2600 Wizard of Wor IQN Score 31190 #10 of 41 Archive leaderboard report
Atari Games Atari 2600 Yars Revenge IQN Score 28379 #15 of 17 Archive leaderboard report
Atari Games Atari 2600 Zaxxon IQN Score 21772 #14 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.

Methods

ConvolutionDQNDense ConnectionsQ-Learning

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