Papers › Rainbow: Combining Improvements in Deep Reinforcement Learning

Rainbow: Combining Improvements in Deep Reinforcement Learning

6 Oct 2017arXiv:1710.02298archive 2025-07-28

Matteo Hessel, Joseph Modayil, Hado van Hasselt, Tom Schaul, Georg Ostrovski, Will Dabney, Dan Horgan, Bilal Piot, Mohammad Azar, David Silver

The deep reinforcement learning community has made several independent improvements to the DQN algorithm. However, it is unclear which of these extensions are complementary and can be fruitfully combined. This paper examines six extensions to the DQN algorithm and empirically studies their combination. Our experiments show that the combination provides state-of-the-art performance on the Atari 2600 benchmark, both in terms of data efficiency and final performance. We also provide results from a detailed ablation study that shows the contribution of each component to overall 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 6 code samples: 5 from 3 repositories linked to this paper, 1 identical to code harvested from another paper's repository. Across all 6: 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 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): 5 samples from 3 repositories, 4 ran (4 with no instrument failure; 0 where Syntology's instrument failed); 1 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.

No sample is linked to this paper from 12 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 5 samples that ran has no recorded date.

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

BY571/DQN-Atari-Agents mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
Curt-Park/rainbow-is-all-you-need mentioned on GitHubMITSyntology: not harvested report
JayLohokare/banana-world-navigation mentioned on GitHubtfSyntology: not harvested report
Kaixhin/Rainbow mentioned on GitHubpytorchMITSyntology: not harvested report
amzoyang/CS-221-Final-Project mentioned on GitHubpytorchSyntology: not harvested report
atavakol/action-hypergraph-networks mentioned on GitHubtfMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Learning to Represent Action Values as a Hypergraph on the Action Vertices (arXiv:2010.14680; that paper's own run record: 4 ran (of which 0 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) · 1 unverified); nothing checks that they implement this paper's method. 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
coreylowman/rl_simply mentioned on GitHubpytorchSyntology: not harvested report
daviddcho/supermario mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Playing Atari with Deep Reinforcement Learning (arXiv:1312.5602; that paper's own run record: 64 ran (of which 24 constructed an object rather than computing a result; 46 with no instrument failure: 5 honoured, 0 violated, 41 with no contract checked; 18 where Syntology's instrument failed) · 53 unverified) and Deep Reinforcement Learning with Double Q-learning (arXiv:1509.06461; that paper's own run record: 56 ran (of which 38 constructed an object rather than computing a result; 55 with no instrument failure: 0 honoured, 0 violated, 55 with no contract checked; 1 where Syntology's instrument failed) · 50 unverified); nothing checks that they implement this paper's method. report
deconlabs/Binanace-trading-simulation mentioned on GitHubpytorchMITSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
deconlabs/Binanace_trading_simulation mentioned on GitHubpytorchMITSyntology: not harvested report
deconlabs/TradingZoo-Dynamic-fee-simulation mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Proximal Policy Optimization Algorithms (arXiv:1707.06347; that paper's own run record: 99 ran (of which 53 constructed an object rather than computing a result; 71 with no instrument failure: 7 honoured, 2 violated, 62 with no contract checked; 28 where Syntology's instrument failed) · 77 unverified); nothing checks that they implement this paper's method. report
dsapandora/s_cera mentioned on GitHubtfGPL-3.0Syntology: not harvested report
eddynelson/dqn mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Playing Atari with Deep Reinforcement Learning (arXiv:1312.5602; that paper's own run record: 64 ran (of which 24 constructed an object rather than computing a result; 46 with no instrument failure: 5 honoured, 0 violated, 41 with no contract checked; 18 where Syntology's instrument failed) · 53 unverified) and Prioritized Experience Replay (arXiv:1511.05952; that paper's own run record: 80 ran (of which 62 constructed an object rather than computing a result; 72 with no instrument failure: 4 honoured, 0 violated, 68 with no contract checked; 8 where Syntology's instrument failed) · 31 unverified); nothing checks that they implement this paper's method. report
efg59/Rainbow mentioned on GitHubSyntology: not harvested report
facebookresearch/Horizon mentioned on GitHubpytorchSyntology: not harvested report
facebookresearch/ReAgent mentioned on GitHubpytorchSyntology: not harvested report
floringogianu/atari-agents mentioned on GitHubpytorchSyntology: not harvested report
htdt/rainbow mentioned on GitHubpytorchSyntology: not harvested report
jacobkooi/hadamax mentioned on GitHubjaxSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
jvoynow/DQN-analysis-with-2048 mentioned on GitHubSyntology: not harvested report
lireer/ricochet-robot-solver mentioned on GitHubSyntology: not harvested report
liuyuezhang/pyrl mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Asynchronous Methods for Deep Reinforcement Learning (arXiv:1602.01783; that paper's own run record: 60 ran (of which 20 constructed an object rather than computing a result; 50 with no instrument failure: 2 honoured, 1 violated, 47 with no contract checked; 10 where Syntology's instrument failed) · 35 unverified) and Proximal Policy Optimization Algorithms (arXiv:1707.06347; that paper's own run record: 99 ran (of which 53 constructed an object rather than computing a result; 71 with no instrument failure: 7 honoured, 2 violated, 62 with no contract checked; 28 where Syntology's instrument failed) · 77 unverified); nothing checks that they implement this paper's method. report
michaelnny/deep_rl_zoo mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Playing Atari with Deep Reinforcement Learning (arXiv:1312.5602; that paper's own run record: 64 ran (of which 24 constructed an object rather than computing a result; 46 with no instrument failure: 5 honoured, 0 violated, 41 with no contract checked; 18 where Syntology's instrument failed) · 53 unverified) and Never Give Up: Learning Directed Exploration Strategies (arXiv:2002.06038; that paper's own run record: 7 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 7 unverified); nothing checks that they implement this paper's method. report
mindspore-courses/Rainbow-MindSpore mentioned on GitHubmindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Prioritized Experience Replay (arXiv:1511.05952; that paper's own run record: 80 ran (of which 62 constructed an object rather than computing a result; 72 with no instrument failure: 4 honoured, 0 violated, 68 with no contract checked; 8 where Syntology's instrument failed) · 31 unverified); nothing checks that they implement this paper's method. report
mingyip/Rainbow-Reinforcement-Learning-For-Chess-Games mentioned on GitHubSyntology: not harvested report
mohith-sakthivel/rainbow_dqn mentioned on GitHubpytorchGPL-3.0Syntology: not harvested report
odokumaci/rainbow-unity-obstacle-tower-challenge mentioned on GitHubSyntology: not harvested report
robintyh1/icml2021-pengqlambda mentioned on GitHubtfMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Addressing Function Approximation Error in Actor-Critic Methods (arXiv:1802.09477; that paper's own run record: 26 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 1 honoured, 2 violated, 17 with no contract checked; 6 where Syntology's instrument failed) · 10 unverified); nothing checks that they implement this paper's method. report
roboticist-by-day/Rainbow_DQN mentioned on GitHubpytorchGPL-3.0Syntology: not harvested report
thu-ml/tianshou mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Tianshou: a Highly Modularized Deep Reinforcement Learning Library (arXiv:2107.14171; 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, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
xusophia/DataSciFinalProj mentioned on GitHubpytorchSyntology: not harvested report
chandar-lab/RLHive pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Playing Atari with Deep Reinforcement Learning (arXiv:1312.5602; that paper's own run record: 64 ran (of which 24 constructed an object rather than computing a result; 46 with no instrument failure: 5 honoured, 0 violated, 41 with no contract checked; 18 where Syntology's instrument failed) · 53 unverified) and Prioritized Experience Replay (arXiv:1511.05952; that paper's own run record: 80 ran (of which 62 constructed an object rather than computing a result; 72 with no instrument failure: 4 honoured, 0 violated, 68 with no contract checked; 8 where Syntology's instrument failed) · 31 unverified); nothing checks that they implement this paper's method. 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

6 samples harvested: 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 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 · honoured contract
1ran · violated contract
3ran
1unverified

Licence: 1 of the 6 samples is 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 3 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. 1 sample is listed last, in a group without a repository. “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/DQN-Atari-Agents community (archive-listed) 1 sample, 0 ran · 1 unverified
run in 143 papers run_atari_dqn.py unverified MIT (permissive) · 34182f569fae27fe · report
deconlabs/Binanace-trading-simulation community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
fnRSI envs/derivative_utils.py ran MIT (permissive) · 46e2342857dcaedf · report fixture: signature m_Df:MockDataFrame/0/?, m_N:int/0/int · returned float64 · level recorded 2026-09-26
get_bollinger_diffs envs/derivative_utils.py ran MIT (permissive) · bc2c6bd2e337d077 · report fixture: signature df:DataFrame/0/?, n:int/0/int, k:int/0/int · returned float64 · level recorded 2026-09-26
get_stochastic envs/derivative_utils.py ran MIT (permissive) · 787e35131a9851ea · report fixture: signature df:DataFrame/0/?, n:int/0/int, m:int/0/int, t:int/0/int · returned float64 · level recorded 2026-09-26
jacobkooi/hadamax community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
straight_through_round purejaxql/pqn_atari_hadamax.py ran · violated contract fingerprinted Apache-2.0 (permissive) · 3f5569362eb33902 · report fixture: signature x:ArrayImpl/1/float · returned ArrayImpl · level recorded 2026-09-22
Repository not located 1 sample, 1 ran (0 instrument-failed) · 0 unverified
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
linear_schedule in 26 papers repository not located ran · honoured contract fingerprinted licence of this copy not recorded · 4c60d8998b722013 · report fixture: signature start_e:float/0/float, end_e:float/0/float, duration:int/0/int, t:int/0/int · returned float · level recorded, date not recorded

Tasks

Atari GamesDeep Reinforcement LearningMontezuma's RevengeReinforcement LearningReinforcement Learning (RL)reinforcement-learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Atari Games Atari 2600 Ms. Pacman Rainbow Score 2570.2 #31 of 47 Archive leaderboard report
Atari Games Atari 2600 Space Invaders Rainbow Score 12629.0 #17 of 55 Archive leaderboard report
Atari Games Atari games Rainbow DQN Mean Human Normalized Score 873.97% #10 of 12 Archive leaderboard report
Atari Games Atari-57 Rainbow DQN Human World Record Breakthrough 4 #9 of 11 Archive leaderboard report
Atari Games Atari-57 Rainbow DQN Mean Human Normalized Score 873.97% #9 of 11 Archive leaderboard report
Atari Games atari game Rainbow Human World Record Breakthrough 4 #9 of 9 Archive leaderboard report
Montezuma's Revenge Atari 2600 Montezuma's Revenge Rainbow Average Return (NoOp) 384 #3 of 3 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: Rainbow DQN

AdamConvolutionDQNDense ConnectionsDouble Q-learningDueling NetworkN-step ReturnsNoisy Linear LayerPrioritized Experience ReplayQ-LearningRainbow DQN

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