Papers › Prioritized Experience Replay

Prioritized Experience Replay

18 Nov 2015arXiv:1511.05952archive 2025-07-28

Tom Schaul, John Quan, Ioannis Antonoglou, David Silver

Experience replay lets online reinforcement learning agents remember and reuse experiences from the past. In prior work, experience transitions were uniformly sampled from a replay memory. However, this approach simply replays transitions at the same frequency that they were originally experienced, regardless of their significance. In this paper we develop a framework for prioritizing experience, so as to replay important transitions more frequently, and therefore learn more efficiently. We use prioritized experience replay in Deep Q-Networks (DQN), a reinforcement learning algorithm that achieved human-level performance across many Atari games. DQN with prioritized experience replay achieves a new state-of-the-art, outperforming DQN with uniform replay on 41 out of 49 games.

PaperPDFCodeCode Syntology ranMethod as code

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 111 code samples: 110 from 40 repositories linked to this paper, 1 identical to code harvested from another paper's repository. Across all 111: 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. Where Syntology's instrument failed: 5 where our contract draft was wrong; 3 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 110 samples from 40 repositories, 79 ran (71 with no instrument failure; 8 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 19 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.

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

1jsingh/rl_navigation mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to 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
7starsea/Prioritized-Experience-Replay mentioned on GitHubMITSyntology: not harvested report
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
Adrelf/DRL-navigation mentioned on GitHubpytorchSyntology: 2 samples, 0 ran · 2 unverified report
Arrabonae/openai_DDDQN mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
Brandon-Rozek/DeepRL mentioned on GitHubSyntology: not harvested report
CSCI4850/S20-team3-project mentioned on GitHubSyntology: 1 sample, 0 ran · 1 unverified report
CharlotteMorrison/Baxter-Research mentioned on GitHubpytorchSyntology: 5 samples, 4 ran (0 instrument-failed) · 1 unverified report
CharlotteMorrison/Baxter-VREP mentioned on GitHubpytorchSyntology: 3 samples, 2 ran (0 instrument-failed) · 1 unverified report
CharlotteMorrison/Baxter-VREP-Version-2 mentioned on GitHubpytorchSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
Clement-Hui/Q-Learning mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
Curt-Park/rainbow-is-all-you-need mentioned on GitHubMITSyntology: not harvested report
Damcy/prioritized-experience-replay mentioned on GitHubtorchSyntology: 4 samples, 3 ran (2 instrument-failed) · 1 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
Guillaume-Cr/lunar_lander_per mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
Howuhh/prioritized_experience_replay mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (1 instrument-failed) · 0 unverified report
HussonnoisMaxence/RL_Algorithms mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
JuliaPOMDP/DeepQLearning.jl mentioned on GitHubNOASSERTIONSyntology: not harvested report
KAIST-AILab/deeprl_practice_colab mentioned on GitHubSyntology: 5 samples, 5 ran (0 instrument-failed) · 0 unverified 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
MEOWMEOW114/nd893-p1-navigation-banana mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to 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
MathPhysSim/PER-NAF mentioned on GitHubtfSyntology: 5 samples, 4 ran (0 instrument-failed) · 1 unverified report
MrDaubinet/collaboration-and-competition mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments (arXiv:1706.02275; that paper's own run record: 75 ran (of which 54 constructed an object rather than computing a result; 68 with no instrument failure: 2 honoured, 0 violated, 66 with no contract checked; 7 where Syntology's instrument failed) · 68 unverified); nothing checks that they implement this paper's method. report
NervanaSystems/coach mentioned on GitHubtfSyntology: not harvested report
OMS1996/Carla_The_RL_Self-Driving-Car mentioned on GitHubtfSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
Remtasya/DDPG-Actor-Critic-Reinforcement-Learning-Reacher-Environment 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); nothing checks that they implement this paper's method. report
SayhoKim/tetrisRL mentioned on GitHubtfSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
SimonRamstedt/ddpg mentioned on GitHubtfSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
Suryavf/SelfDrivingCar mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified 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
VasaKiDD/TD3-deep-rl-research mentioned on GitHubpytorchSyntology: 3 samples, 2 ran (1 instrument-failed) · 1 unverified report
VictorZuanazzi/Project_RL mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
ameet-1997/Prioritized_Experience_Replay mentioned on GitHubtorchMITSyntology: not harvested report
anhtu293/NeurIPS-2019-Challenge mentioned on GitHubtfSyntology: not harvested report
atavakol/action-branching-agents mentioned on GitHubtfSyntology: 5 samples, 4 ran (0 instrument-failed) · 1 unverified 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
austinsilveria/Banana-Collection-DQN mentioned on GitHubpytorchSyntology: not harvested report
backgom2357/Recommender_system_via_deep_RL mentioned on GitHubtfSyntology: 3 samples, 2 ran (0 instrument-failed) · 1 unverified 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
cocolico14/N-step-Dueling-DDQN-PER-Pacman mentioned on GitHubSyntology: 1 sample, 0 ran · 1 unverified report
dtak/hip-mdp-public mentioned on GitHubtfSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
eddynelson/dqn mentioned on GitHubtfSyntology: 1 sample, 0 ran · 1 unverified report
emiled16/Beyond_prioritized_experience_replay mentioned on GitHubpytorchSyntology: 5 samples, 4 ran (0 instrument-failed) · 1 unverified report
guillaumeboniface/bananaland mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to 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
iDataist/Continuous-Control-with-Deep-Deterministic-Policy-Gradient mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Continuous control with deep reinforcement learning (arXiv:1509.02971; that paper's own run record: 163 ran (of which 126 constructed an object rather than computing a result; 152 with no instrument failure: 3 honoured, 0 violated, 149 with no contract checked; 11 where Syntology's instrument failed) · 143 unverified); nothing checks that they implement this paper's method. report
iDataist/Navigation-with-Deep-Q-Network mentioned on GitHubpytorchMITSyntology: not harvested report
iDataist/Tennis-With-Multi-Agent-Reinforcement mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Continuous control with deep reinforcement learning (arXiv:1509.02971; that paper's own run record: 163 ran (of which 126 constructed an object rather than computing a result; 152 with no instrument failure: 3 honoured, 0 violated, 149 with no contract checked; 11 where Syntology's instrument failed) · 143 unverified); nothing checks that they implement this paper's method. report
instadeepai/flashbax mentioned on GitHubjaxApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Podracer architectures for scalable Reinforcement Learning (arXiv:2104.06272; that paper's own run record: 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) · 1 unverified); nothing checks that they implement this paper's method. report
justinmaojones/starr mentioned on GitHubSyntology: 2 samples, 1 ran (1 instrument-failed) · 1 unverified report
kayuksel/pytorch-ars mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Simple random search provides a competitive approach to reinforcement learning (arXiv:1803.07055; that paper's own run record: 13 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
kmdanielduan/DQN_Family_PyTorch mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
ku2482/sac-discrete.pytorch mentioned on GitHubpytorchSyntology: 6 samples, 6 ran (0 instrument-failed) · 0 unverified report
ku2482/soft-actor-critic.pytorch mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Dropout Q-Functions for Doubly Efficient Reinforcement Learning (arXiv:2110.02034; that paper's own run record: 6 ran (of which 3 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
mindspore-courses/Deep-Reinforcement-Learning-Algorithms-with-MindSpore mentioned on GitHubmindsporeSyntology: not harvested report
mindspore-courses/Rainbow-MindSpore mentioned on GitHubmindsporeSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
nbopardi/smb mentioned on GitHubtfSyntology: 1 sample, 0 ran · 1 unverified report
olonok69/Udacity_Banana_Unity mentioned on GitHubpytorchSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
rybread1/DeepRlTrex mentioned on GitHubtfnot reachable when probed 2026-09-18 — repositories for recent papers often appear after camera-readySyntology: not harvested report
rybread1/deep-rl-trex mentioned on GitHubtfnot reachable when probed 2026-09-18 — repositories for recent papers often appear after camera-readySyntology: not harvested report
seacevedo/ReinforcementLearningProjects mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
shashwatsaxena571/DRL-navigation mentioned on GitHubpytorchnot reachable when probed 2026-09-18 — repositories for recent papers often appear after camera-readySyntology: not harvested report
snhwang/p1_navigation_SNH mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
snhwang/p2-continuous-control-SNH mentioned on GitHubpytorchSyntology: not harvested report
snhwang/p3_collab-compet mentioned on GitHubpytorchSyntology: not harvested report
sunfex/weighted-sac mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
tensorlayer/RLzoo mentioned on GitHubtfSyntology: 5 samples, 4 ran (0 instrument-failed) · 1 unverified report
toshikwa/soft-actor-critic.pytorch mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Stochastic MeanFlow Policies: One-Step Generative Control with Entropic Mirror Descent (arXiv:2605.21282; that paper's own run record: 13 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 6 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
tphanson/xupr-drl mentioned on GitHubtfMITSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
utarumo/RL_implementation mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to 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
xinjinghao/sparrow-v1 mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World (arXiv:1703.06907; that paper's own run record: 5 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; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
xusophia/DataSciFinalProj mentioned on GitHubpytorchSyntology: not harvested report
yusme/DDPG mentioned on GitHubtfnot reachable when probed 2026-09-18 — repositories for recent papers often appear after camera-readySyntology: not harvested report
yzheng51/rl-dino-run mentioned on GitHubpytorchSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
chandar-lab/RLHive pytorchSyntology: 9 samples, 6 ran (1 instrument-failed) · 3 unverified report
hill-a/stable-baselines tfSyntology: 10 samples, 6 ran (2 instrument-failed) · 4 unverified report
labmlai/annotated_deep_learning_paper_implementations pytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 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

111 samples harvested: 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. “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.

4ran · honoured contract
5ran · our draft was wrong
3ran; the contract check could not run
68ran
31unverified

Licence: 43 of the 111 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 40 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.

Adrelf/DRL-navigation community (archive-listed) 2 samples, 0 ran · 2 unverified
PrioritizedReplayBuffer utils/memory.py unverified no licence file found · pointer only · c647f62c4b7e10cb · report
ReplayBuffer in 33 papers utils/memory.py unverified no licence file found · pointer only · 7859b3965dc78ae3 · report
Arrabonae/openai_DDDQN community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
ReplayBuffer in 33 papers replay.py ran Apache-2.0 (permissive) · 82024cb507cb1dee · report fixture: returned ReplayBuffer · level recorded 2026-09-22
CSCI4850/S20-team3-project community (archive-listed) 1 sample, 0 ran · 1 unverified
ReplayMemory in 11 papers DoubleQ/Prioritized/ReplayMemory.py unverified MIT (permissive) · 8735a7421b0a382d · report
CharlotteMorrison/Baxter-Research community (archive-listed) 5 samples, 4 ran (0 instrument-failed) · 1 unverified
MinSegmentTree td3algorithm/priority-replay/prioritized_replay_buffer.py ran no licence file found · pointer only · 077ddff310bef0b1 · report fixture: returned MinSegmentTree · level recorded 2026-09-22
ReplayBuffer in 33 papers td3algorithm/priority-replay/prioritized_replay_buffer.py ran no licence file found · pointer only · e13397d005876228 · report fixture: returned ReplayBuffer · level recorded 2026-09-22
SegmentTree td3algorithm/priority-replay/prioritized_replay_buffer.py ran no licence file found · pointer only · 857b5b82ec1ef85f · report fixture: returned SegmentTree · level recorded 2026-09-22
SumSegmentTree td3algorithm/priority-replay/prioritized_replay_buffer.py ran no licence file found · pointer only · c213d128135c8d6c · report fixture: returned SumSegmentTree · level recorded 2026-09-22
PrioritizedReplayBuffer td3algorithm/priority-replay/prioritized_replay_buffer.py unverified no licence file found · pointer only · b4f87ad2ad0b0c33 · report
CharlotteMorrison/Baxter-VREP community (archive-listed) 3 samples, 2 ran (0 instrument-failed) · 1 unverified
ReplayBuffer in 33 papers td3/experience/priority_replay_buffer.py ran no licence file found · pointer only · c2cbd2d0d7d66167 · report fixture: returned ReplayBuffer · level recorded 2026-09-22
SumSegmentTree td3/experience/priority_replay_buffer.py ran no licence file found · pointer only · 25c1b3ae5e411f3d · report fixture: returned SumSegmentTree · level recorded 2026-09-22
PrioritizedReplayBuffer td3/experience/priority_replay_buffer.py unverified no licence file found · pointer only · 88f31f7047df86cf · report
CharlotteMorrison/Baxter-VREP-Version-2 community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
ReplayBuffer in 33 papers td3/experience/priority_replay_buffer.py ran no licence file found · pointer only · a1b54613a3985829 · report fixture: returned ReplayBuffer · level recorded 2026-09-22
PrioritizedReplayBuffer td3/experience/priority_replay_buffer.py unverified no licence file found · pointer only · 775b4f4f37c0e3ac · report
Clement-Hui/Q-Learning community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
PERReplayMemory replaymemory.py ran no licence file found · pointer only · cffa9035057e30ee · report fixture: returned PERReplayMemory · level recorded 2026-09-22
ReplayMemory in 11 papers replaymemory.py ran no licence file found · pointer only · 176c97171a30da8b · report fixture: returned ReplayMemory · level recorded 2026-09-22
Damcy/prioritized-experience-replay community (archive-listed) 4 samples, 3 ran (2 instrument-failed) · 1 unverified
BinaryHeap rank_based.py ran MIT (permissive) · cd01aba8f501b37d · report fixture: returned BinaryHeap · level recorded 2026-09-22
exchange_key_value rank_based.py ran · our draft was wrong MIT (permissive) · 33c2d867cbd21fad · report fixture: signature in_dict:dict/0/? · returned dict · level recorded 2026-09-22
list_to_dict in 8 papers rank_based.py ran · our draft was wrong fingerprinted MIT (permissive) · 04747a180661f699 · report fixture: signature in_list:list/1/int · returned dict · level recorded 2026-09-22
Experience in 5 papers rank_based.py unverified MIT (permissive) · 02ee81b07942c502 · report
Guillaume-Cr/lunar_lander_per community (archive-listed) 1 sample, 0 ran · 1 unverified
ReplayBuffer in 33 papers replay_buffer.py unverified no licence file found · pointer only · f426229e0c5e2d70 · report
Howuhh/prioritized_experience_replay community (archive-listed) 3 samples, 3 ran (1 instrument-failed) · 0 unverified
PrioritizedReplayBuffer memory/buffer.py ran MIT (permissive) · 9e9658f9014474b4 · report fixture: returned PrioritizedReplayBuffer · level recorded 2026-09-22
SumTree memory/buffer.py ran · metamorphic tier: deterministic MIT (permissive) · c325494e00497bfc · report fixture: returned SumTree · level recorded 2026-09-22
device in 8 papers memory/buffer.py ran · our draft was wrong MIT (permissive) · 21a7a1ad47b2bc08 · report fixture: signature force_cpu:bool/0/bool · returned str · level recorded 2026-09-22
HussonnoisMaxence/RL_Algorithms community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
PrioritisedExperienceReplay QLearning/PriotisedExperienceReplay/PrioritisedBuffer.py ran no licence file found · pointer only · 68bf90ac9c0b86f0 · report fixture: returned PrioritisedExperienceReplay · level recorded 2026-09-22
KAIST-AILab/deeprl_practice_colab community (archive-listed) 5 samples, 5 ran (0 instrument-failed) · 0 unverified
Memory in 19 papers rllab/dqn/misc/memory_pool.py ran no licence file found · pointer only · 4f033d771152e1b0 · report fixture: returned Memory · level recorded 2026-09-22
RingBuffer rllab/dqn/misc/memory_pool.py ran no licence file found · pointer only · 9f955f399cfeca91 · report fixture: returned RingBuffer · level recorded 2026-09-22
SequentialMemory rllab/dqn/misc/memory_pool.py ran no licence file found · pointer only · 3ca0a6aa1ff1103b · report fixture: returned SequentialMemory · level recorded 2026-09-22
sample_batch_indexes in 5 papers rllab/dqn/misc/memory_pool.py ran · honoured contract fingerprinted no licence file found · pointer only · 1988a1e36a96fc82 · report fixture: signature low:int/0/int, high:int/0/int, size:int/0/int · returned list · level recorded 2026-09-22
zeroed_observation rllab/dqn/misc/memory_pool.py ran · honoured contract fingerprinted no licence file found · pointer only · f7637a32ccd5a616 · report fixture: signature observation:ndarray/2/float · returned ndarray · level recorded 2026-09-22
MathPhysSim/PER-NAF community (archive-listed) 5 samples, 4 ran (0 instrument-failed) · 1 unverified
MinSegmentTree pernaf/pernaf/utils/prioritised_experience_replay.py ran MIT (permissive) · 7a8ccb9efbfef877 · report fixture: returned MinSegmentTree · level recorded 2026-09-22
ReplayBuffer in 33 papers pernaf/pernaf/utils/prioritised_experience_replay.py ran MIT (permissive) · 46cf03e4d4b628c3 · report fixture: returned ReplayBuffer · level recorded 2026-09-22
SegmentTree pernaf/pernaf/utils/prioritised_experience_replay.py ran MIT (permissive) · 3d07d5a92b97866f · report fixture: returned SegmentTree · level recorded 2026-09-22
SumSegmentTree pernaf/pernaf/utils/prioritised_experience_replay.py ran MIT (permissive) · 06dc39c20552ec26 · report fixture: returned SumSegmentTree · level recorded 2026-09-22
PrioritizedReplayBuffer pernaf/pernaf/utils/prioritised_experience_replay.py unverified MIT (permissive) · 8beaa28b0b260aaa · report
OMS1996/Carla_The_RL_Self-Driving-Car community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
PrioritizedReplayBuffer Full_Script/FULL_SCRIPT.py ran no licence file found · pointer only · 5147fd4abb094a4a · report fixture: returned PrioritizedReplayBuffer · level recorded 2026-09-22
SayhoKim/tetrisRL community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
ReplayBuffer in 33 papers lib/utils/replay_buffer.py ran no licence file found · pointer only · 867fd67d42cbe6f4 · report fixture: returned ReplayBuffer · level recorded 2026-09-22
PrioritizedReplayBuffer lib/utils/replay_buffer.py unverified no licence file found · pointer only · 19719efbf3a172f2 · report
SimonRamstedt/ddpg community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
ReplayMemory in 11 papers replay_memory.py ran · metamorphic tier: deterministic MIT (permissive) · 5b683309331178dc · report fixture: returned ReplayMemory · level recorded 2026-09-22
Suryavf/SelfDrivingCar community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
PrioritizedExperienceReplay common/prioritized.py ran MIT (permissive) · 7a9dbbb83432ce56 · report fixture: returned PrioritizedExperienceReplay · level recorded 2026-09-22
VasaKiDD/TD3-deep-rl-research community (archive-listed) 3 samples, 2 ran (1 instrument-failed) · 1 unverified
PrioritizeBuffer buffer/FAIreplaybuffer.py ran Apache-2.0 (permissive) · a946469f4db97a17 · report fixture: returned PrioritizeBuffer · level recorded 2026-09-22
relativize buffer/FAIreplaybuffer.py ran; the contract check could not run (RAISES) fingerprinted Apache-2.0 (permissive) · 98104ac19ccdde37 · report fixture: signature x:ndarray/1/float · returned ndarray · level recorded 2026-09-22
calculate_vrs buffer/FAIreplaybuffer.py unverified Apache-2.0 (permissive) · d4b670306e938111 · report
VictorZuanazzi/Project_RL community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
PrioritizedReplayMemory code/replay.py ran no licence file found · pointer only · 47564a504f4f0ba8 · report fixture: returned PrioritizedReplayMemory · level recorded 2026-09-22
RankBased code/replay.py ran no licence file found · pointer only · 4e74fb757285572a · report fixture: returned RankBased · level recorded 2026-09-22
SumTree code/replay.py ran no licence file found · pointer only · 72934503a23565c0 · report fixture: returned SumTree · level recorded 2026-09-22
atavakol/action-branching-agents community (archive-listed) 5 samples, 4 ran (0 instrument-failed) · 1 unverified
MinSegmentTree agents/bdq/deepq/replay_buffer.py ran MIT (permissive) · 8220d704dacacc71 · report fixture: returned MinSegmentTree · level recorded 2026-09-22
ReplayBuffer in 33 papers agents/bdq/deepq/replay_buffer.py ran MIT (permissive) · f6c715a36c9b0278 · report fixture: returned ReplayBuffer · level recorded 2026-09-22
SegmentTree agents/bdq/deepq/replay_buffer.py ran MIT (permissive) · 56e375a0071d0782 · report fixture: returned SegmentTree · level recorded 2026-09-22
SumSegmentTree agents/bdq/deepq/replay_buffer.py ran MIT (permissive) · 7e730f8947dd1481 · report fixture: returned SumSegmentTree · level recorded 2026-09-22
PrioritizedReplayBuffer agents/bdq/deepq/replay_buffer.py unverified MIT (permissive) · f2765362ca9308ec · report
backgom2357/Recommender_system_via_deep_RL community (archive-listed) 3 samples, 2 ran (0 instrument-failed) · 1 unverified
MinTree replay_buffer.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 5f169c1caea8a550 · report fixture: signature priority:float/0/float · returned NoneType · level recorded 2026-09-22
SumTree replay_buffer.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · fba39114f708780e · report fixture: signature priority:float/0/float · returned NoneType · level recorded 2026-09-22
PriorityExperienceReplay replay_buffer.py unverified no licence file found · pointer only · 48d5f5fe1d46235b · report
cocolico14/N-step-Dueling-DDQN-PER-Pacman community (archive-listed) 1 sample, 0 ran · 1 unverified
Agent in 42 papers agent.py unverified MIT (permissive) · 7301cd0334b1ec18 · report
dtak/hip-mdp-public community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
PriorityQueue ExperienceReplay.py ran MIT (permissive) · ebc11e08646052be · report fixture: returned PriorityQueue · level recorded 2026-09-22
ExperienceReplay in 5 papers ExperienceReplay.py unverified MIT (permissive) · 62c9777a79904b2f · report
eddynelson/dqn community (archive-listed) 1 sample, 0 ran · 1 unverified
ReplayMemory in 11 papers dqn/replay_memory/replay_memory.py unverified Apache-2.0 (permissive) · 64f1fd20f4b6af5d · report
emiled16/Beyond_prioritized_experience_replay community (archive-listed) 5 samples, 4 ran (0 instrument-failed) · 1 unverified
MinSegmentTree final_buffer.py ran no licence file found · pointer only · 6c8077ee353ea8dd · report fixture: returned MinSegmentTree · level recorded 2026-09-22
ReplayBuffer in 33 papers final_buffer.py ran no licence file found · pointer only · 4dfb2bb869a28e56 · report fixture: returned ReplayBuffer · level recorded 2026-09-22
SegmentTree final_buffer.py ran no licence file found · pointer only · bccac243c5d88b63 · report fixture: returned SegmentTree · level recorded 2026-09-22
SumSegmentTree final_buffer.py ran no licence file found · pointer only · cb9820f2f445b8c7 · report fixture: returned SumSegmentTree · level recorded 2026-09-22
PrioritizedReplayBuffer final_buffer.py unverified no licence file found · pointer only · d866cc81fee6dab4 · report
justinmaojones/starr community (archive-listed) 2 samples, 1 ran (1 instrument-failed) · 1 unverified
_temporarily_enable_update starr/sumtree_array.py ran · our draft was wrong MIT (permissive) · 8aac36c3449d1450 · report fixture: signature func:callable/0/? · returned function · level recorded 2026-09-22
SumTreeArray starr/sumtree_array.py unverified MIT (permissive) · 0e783398ca755fde · report
kmdanielduan/DQN_Family_PyTorch community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
PrioritizedReplayMemory memory.py ran no licence file found · pointer only · e9a7eb1cb21539cf · report fixture: returned PrioritizedReplayMemory · level recorded 2026-09-22
SumTree memory.py ran no licence file found · pointer only · b414f4c639de69a4 · report fixture: returned SumTree · level recorded 2026-09-22
ku2482/sac-discrete.pytorch community (archive-listed) 6 samples, 6 ran (0 instrument-failed) · 0 unverified
LazyMemory sacd/memory/per.py ran MIT (permissive) · 5e1b891a436b2bb5 · report fixture: returned LazyMemory · level recorded 2026-09-22
LazyMultiStepMemory sacd/memory/per.py ran MIT (permissive) · 108ae49edfcc0ba7 · report fixture: returned LazyMultiStepMemory · level recorded 2026-09-22
LazyPrioritizedMultiStepMemory sacd/memory/per.py ran MIT (permissive) · 7303883fa36b6ce2 · report fixture: returned LazyPrioritizedMultiStepMemory · level recorded 2026-09-22
MinTree sacd/memory/per.py ran MIT (permissive) · c2c7b84d96ab9ab8 · report fixture: returned MinTree · level recorded 2026-09-22
SegmentTree sacd/memory/per.py ran MIT (permissive) · 16e63d2f53eb184c · report fixture: returned SegmentTree · level recorded 2026-09-22
SumTree sacd/memory/per.py ran MIT (permissive) · 1d958381328691cb · report fixture: returned SumTree · level recorded 2026-09-22
mindspore-courses/Rainbow-MindSpore community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
SegmentTree segment_tree.py ran Apache-2.0 (permissive) · 202fb1a633c0ff87 · report fixture: returned SegmentTree · level recorded 2026-09-22
SumSegmentTree segment_tree.py ran Apache-2.0 (permissive) · 524925816c70a4d4 · report fixture: returned SumSegmentTree · level recorded 2026-09-22
nbopardi/smb community (archive-listed) 1 sample, 0 ran · 1 unverified
ReplayBuffer in 33 papers dqn_utils.py unverified no licence file found · pointer only · 1f3901918f090c5e · report
olonok69/Udacity_Banana_Unity community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
SumTree src/buffers.py ran · metamorphic tier: well formed fingerprinted no licence file found · pointer only · 54181e11cf32f132 · report fixture: signature s:float/0/float · returned tuple · level recorded 2026-09-22
PrioritizedReplayBuffer src/buffers.py unverified no licence file found · pointer only · 4f0e2f922875b443 · report
seacevedo/ReinforcementLearningProjects community (archive-listed) 1 sample, 0 ran · 1 unverified
ReplayBuffer in 33 papers PER.py unverified no licence file found · pointer only · 4ec9642b187da0b4 · report
snhwang/p1_navigation_SNH community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
ReplayBufferPrioritized dqn_agent.py ran no licence file found · pointer only · aa138cc7fbe633b7 · report fixture: returned ReplayBufferPrioritized · level recorded 2026-09-22
sunfex/weighted-sac community (archive-listed) 1 sample, 0 ran · 1 unverified
ReplayMemory in 11 papers replay_memory.py unverified MIT (permissive) · d72a76b37a40fe81 · report
tensorlayer/RLzoo community (archive-listed) 5 samples, 4 ran (0 instrument-failed) · 1 unverified
MinSegmentTree rlzoo/common/buffer.py ran Apache-2.0 (permissive) · d71f774dbe2ff781 · report fixture: returned MinSegmentTree · level recorded 2026-09-22
ReplayBuffer in 33 papers rlzoo/common/buffer.py ran Apache-2.0 (permissive) · f4455aa8614ee649 · report fixture: returned ReplayBuffer · level recorded 2026-09-22
SegmentTree rlzoo/common/buffer.py ran Apache-2.0 (permissive) · a0e91d8061b7a6a7 · report fixture: returned SegmentTree · level recorded 2026-09-22
SumSegmentTree rlzoo/common/buffer.py ran Apache-2.0 (permissive) · 41133b037c07a86e · report fixture: returned SumSegmentTree · level recorded 2026-09-22
PrioritizedReplayBuffer rlzoo/common/buffer.py unverified Apache-2.0 (permissive) · 1bdd3acaa3794f89 · report
tphanson/xupr-drl community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
build_mask helper/utils.py ran MIT (permissive) · f8c03fb7fa67ed3e · report fixture: signature batch_size:int/0/int, num_of_atoms:int/0/int · returned EagerTensor · level recorded 2026-09-26
parse_experiences helper/utils.py ran MIT (permissive) · 45f93c7630b7a4a5 · report fixture: signature experiences:Experiences/0/?, prev_n_steps:int/0/int, n_steps:int/0/int · returned tuple · level recorded 2026-09-26
yzheng51/rl-dino-run community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
ReplayMemory in 11 papers memory.py ran MIT (permissive) · 1707b7c98445e28d · report fixture: returned ReplayMemory · level recorded 2026-09-22
PrioritizedReplayMemory memory.py unverified MIT (permissive) · b7f7d68037ff8f77 · report
chandar-lab/RLHive community (archive-listed) 9 samples, 6 ran (1 instrument-failed) · 3 unverified
CircularReplayBuffer hive/replays/prioritized_replay.py ran MIT (permissive) · 676158087d7ee2f4 · report fixture: returned CircularReplayBuffer · level recorded 2026-09-22
Registrable hive/replays/prioritized_replay.py ran MIT (permissive) · 0a230e75088d0df9 · report fixture: returned Registrable · level recorded 2026-09-22
Seeder hive/replays/prioritized_replay.py ran MIT (permissive) · 9951ee949d6a5db4 · report fixture: returned Seeder · level recorded 2026-09-22
SumTree hive/replays/prioritized_replay.py ran MIT (permissive) · c846b5d272c1064c · report fixture: returned SumTree · level recorded 2026-09-22
numpify hive/replays/prioritized_replay.py ran · honoured contract MIT (permissive) · 3d0319cd2eb82ce4 · report fixture: signature t:Tensor/2/float · returned ndarray · level recorded 2026-09-22
str_to_dtype hive/replays/prioritized_replay.py ran · our draft was wrong MIT (permissive) · f03d8581a6aa79f1 · report fixture: signature dtype:str/0/str · returned type · level recorded 2026-09-22
BaseReplayBuffer hive/replays/prioritized_replay.py unverified MIT (permissive) · 4341a7ea85a43e52 · report
PrioritizedReplayBuffer hive/replays/prioritized_replay.py unverified MIT (permissive) · 216da44371bc1ccf · report
create_folder hive/replays/prioritized_replay.py unverified MIT (permissive) · 8c9564667fc77eb4 · report
hill-a/stable-baselines community (archive-listed) 10 samples, 6 ran (2 instrument-failed) · 4 unverified
MinSegmentTree stable_baselines/common/buffers.py ran MIT (permissive) · 4ecdc9c62de0fbdd · report fixture: returned MinSegmentTree · level recorded 2026-09-22
RunningMeanStd in 13 papers stable_baselines/common/buffers.py ran MIT (permissive) · a7d869ac145d41f2 · report fixture: returned RunningMeanStd · level recorded 2026-09-22
SegmentTree stable_baselines/common/buffers.py ran MIT (permissive) · e5cc36169a42bee6 · report fixture: returned SegmentTree · level recorded 2026-09-22
SumSegmentTree stable_baselines/common/buffers.py ran MIT (permissive) · 6c7690e1fbd0d444 · report fixture: returned SumSegmentTree · level recorded 2026-09-22
tile_images in 10 papers stable_baselines/common/buffers.py ran; the contract check could not run (RAISES) MIT (permissive) · 2ce3f84e5b1bcd28 · report fixture: signature img_nhwc:ndarray/4/float · returned ndarray · level recorded 2026-09-22
unique in 30 papers stable_baselines/common/buffers.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · cf11c744c61b2185 · report fixture: signature sorted_array:ndarray/1/int · returned ndarray · level recorded 2026-09-22
PrioritizedReplayBuffer stable_baselines/common/buffers.py unverified MIT (permissive) · d697d515f0e8ab96 · report
ReplayBuffer in 33 papers stable_baselines/common/buffers.py unverified MIT (permissive) · f5eb1be22a186f73 · report
VecEnvWrapper stable_baselines/common/buffers.py unverified MIT (permissive) · ea40e47a1e6b3da8 · report
VecNormalize stable_baselines/common/buffers.py unverified MIT (permissive) · 06ea1cd53da99b35 · report
labmlai/annotated_deep_learning_paper_implementations community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
ReplayBuffer in 33 papers labml_nn/rl/dqn/replay_buffer.py ran MIT (permissive) · 6e5e90f57a133b61 · report fixture: signature obs:ndarray/3/int, action:int/0/int, reward:float/0/float, next_obs:ndarray/3/int, done:bool/0/bool · returned NoneType · level recorded 2026-09-24
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.
sample_n_unique repository not located ran · honoured contract licence of this copy not recorded · 7075d6afeb7b8d73 · report fixture: signature sampling_f:callable/0/?, n:int/0/int · returned list · level recorded 2026-09-22

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

45 assemblies on this paper: 45 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

45 sibling assemblies for PRIORITIZED EXPERIENCE REPLAY (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another. Bricks printed for 12 of 45 sibling assemblies; the other 33 are listed with their counts; every brick is in this page's JSON twin.

harvested Assembly for PRIORITIZED EXPERIENCE REPLAY (graph method: PRIORITIZED EXPERIENCE REPLAY). 5 bricks; individually on a fixture: 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) · 1 unverified; every one of the 4 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 45 siblings

  1. PrioritizedReplayBuffer entry · level 0 · unverified · b4f87ad2ad0b0c33
  2. MinSegmentTree helper · level 1 · ran · 077ddff310bef0b1
  3. ReplayBuffer helper · level 1 · ran · e13397d005876228
  4. SumSegmentTree helper · level 1 · ran · c213d128135c8d6c
  5. SegmentTree helper · level 1 · ran · 857b5b82ec1ef85f

harvested Assembly for PRIORITIZED EXPERIENCE REPLAY (graph method: PRIORITIZED EXPERIENCE REPLAY). 5 bricks; individually on a fixture: 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) · 1 unverified; every one of the 4 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 45 siblings

  1. PrioritizedReplayBuffer entry · level 0 · unverified · d866cc81fee6dab4
  2. MinSegmentTree helper · level 1 · ran · 6c8077ee353ea8dd
  3. ReplayBuffer helper · level 1 · ran · 4dfb2bb869a28e56
  4. SumSegmentTree helper · level 1 · ran · cb9820f2f445b8c7
  5. SegmentTree helper · level 1 · ran · bccac243c5d88b63

harvested Assembly for PRIORITIZED EXPERIENCE REPLAY (graph method: PRIORITIZED EXPERIENCE REPLAY). 2 bricks; individually on a fixture: 2 ran (of which 2 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; every one of the 2 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 45 siblings

  1. PrioritizedReplayMemory entry · level 1 · ran · e9a7eb1cb21539cf
  2. SumTree helper · level 1 · ran · b414f4c639de69a4

harvested Assembly for PRIORITIZED EXPERIENCE REPLAY (graph method: PRIORITIZED EXPERIENCE REPLAY). 9 bricks; individually on a fixture: 6 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

one of 45 siblings

  1. PrioritizedReplayBuffer entry · level 0 · unverified · 216da44371bc1ccf
  2. CircularReplayBuffer helper · level 1 · ran · 676158087d7ee2f4
  3. SumTree helper · level 1 · ran · c846b5d272c1064c
  4. numpify helper · level 1 · ran · honoured contract · 3d0319cd2eb82ce4
  5. BaseReplayBuffer helper · level 0 · unverified · 4341a7ea85a43e52
  6. create_folder helper · level 0 · unverified · 8c9564667fc77eb4
  7. str_to_dtype helper · level 1 · ran · our draft was wrong · f03d8581a6aa79f1
  8. Registrable helper · level 1 · ran · 0a230e75088d0df9
  9. Seeder helper · level 1 · ran · 9951ee949d6a5db4

harvested Assembly for PRIORITIZED EXPERIENCE REPLAY (graph method: PRIORITIZED EXPERIENCE REPLAY). 5 bricks; individually on a fixture: 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) · 1 unverified; every one of the 4 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 45 siblings

  1. PrioritizedReplayBuffer entry · level 0 · unverified · 88f31f7047df86cf
  2. MinSegmentTree helper · level 1 · ran · 077ddff310bef0b1
  3. ReplayBuffer helper · level 1 · ran · c2cbd2d0d7d66167
  4. SumSegmentTree helper · level 1 · ran · 25c1b3ae5e411f3d
  5. SegmentTree helper · level 1 · ran · 857b5b82ec1ef85f

harvested Assembly for PRIORITIZED EXPERIENCE REPLAY (graph method: PRIORITIZED EXPERIENCE REPLAY). 2 bricks; individually on a fixture: 1 ran (of which 1 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) · 1 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 45 siblings

  1. ExperienceReplay entry · level 0 · unverified · 62c9777a79904b2f
  2. PriorityQueue helper · level 1 · ran · ebc11e08646052be

harvested Assembly for PRIORITIZED EXPERIENCE REPLAY (graph method: PRIORITIZED EXPERIENCE REPLAY). 5 bricks; individually on a fixture: 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) · 1 unverified; every one of the 4 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 45 siblings

  1. PrioritizedReplayBuffer entry · level 0 · unverified · 1bdd3acaa3794f89
  2. MinSegmentTree helper · level 1 · ran · d71f774dbe2ff781
  3. ReplayBuffer helper · level 1 · ran · f4455aa8614ee649
  4. SumSegmentTree helper · level 1 · ran · 41133b037c07a86e
  5. SegmentTree helper · level 1 · ran · a0e91d8061b7a6a7

harvested Assembly for PRIORITIZED EXPERIENCE REPLAY (graph method: PRIORITIZED EXPERIENCE REPLAY). 5 bricks; individually on a fixture: 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) · 1 unverified; every one of the 4 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 45 siblings

  1. PrioritizedReplayBuffer entry · level 0 · unverified · f2765362ca9308ec
  2. MinSegmentTree helper · level 1 · ran · 8220d704dacacc71
  3. ReplayBuffer helper · level 1 · ran · f6c715a36c9b0278
  4. SumSegmentTree helper · level 1 · ran · 7e730f8947dd1481
  5. SegmentTree helper · level 1 · ran · 56e375a0071d0782

harvested Assembly for PRIORITIZED EXPERIENCE REPLAY (graph method: PRIORITIZED EXPERIENCE REPLAY). 1 brick; individually on a fixture: 1 ran (of which 1 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; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 45 siblings

  1. PrioritizedReplayBuffer entry · level 1 · ran · 5147fd4abb094a4a

harvested Assembly for PRIORITIZED EXPERIENCE REPLAY (graph method: PRIORITIZED EXPERIENCE REPLAY). 3 bricks; individually on a fixture: 3 ran (of which 2 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) · 0 unverified. The assembly has not been run end-to-end.

one of 45 siblings

  1. PrioritizedReplayBuffer entry · level 1 · ran · 9e9658f9014474b4
  2. SumTree helper · level 1 · ran · c325494e00497bfc
  3. device helper · level 1 · ran · our draft was wrong · 21a7a1ad47b2bc08

harvested Assembly for PRIORITIZED EXPERIENCE REPLAY (graph method: PRIORITIZED EXPERIENCE REPLAY). 5 bricks; individually on a fixture: 5 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 45 siblings

  1. SequentialMemory entry · level 1 · ran · 3ca0a6aa1ff1103b
  2. Memory helper · level 1 · ran · 4f033d771152e1b0
  3. RingBuffer helper · level 1 · ran · 9f955f399cfeca91
  4. sample_batch_indexes helper · level 1 · ran · honoured contract · 1988a1e36a96fc82
  5. zeroed_observation helper · level 1 · ran · honoured contract · f7637a32ccd5a616

harvested Assembly for PRIORITIZED EXPERIENCE REPLAY (graph method: PRIORITIZED EXPERIENCE REPLAY). 1 brick; individually on a fixture: 1 ran (of which 1 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; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 45 siblings

  1. ReplayBuffer entry · level 1 · ran · 82024cb507cb1dee
  1. PrioritizedReplayBuffer · 346e55b919d31278 · 5 bricks; individually on a fixture: 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) · 1 unverified; every one of the 4 samples that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[12] in the JSON twin
  2. ReplayBufferPrioritized · 43522fce1b108f2e · 1 brick; individually on a fixture: 1 ran (of which 1 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; the one sample that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[13] in the JSON twin
  3. ReplayBuffer · 451a4bd9c8093af7 · 1 brick; individually on a fixture: 1 ran (of which 1 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; the one sample that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[14] in the JSON twin
  4. ReplayMemory · 4676496469079ae2 · 1 brick; individually on a fixture: 1 ran (of which 1 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; the one sample that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[15] in the JSON twin
  5. PrioritizedReplayBuffer · 49998ff54382b18c · 5 bricks; individually on a fixture: 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) · 1 unverified; every one of the 4 samples that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[16] in the JSON twin
  6. PrioritizedReplayBuffer · 55dcf1fa8b4cbbb9 · 5 bricks; individually on a fixture: 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) · 1 unverified; every one of the 4 samples that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[17] in the JSON twin
  7. ReplayBuffer · 58a8adeece95dcd1 · 3 bricks; individually on a fixture: 2 ran (of which 2 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; every one of the 2 samples that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[18] in the JSON twin
  8. SumTree · 59e0a5c8ca54092e · 1 brick; individually on a fixture: 1 ran (of which 1 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; the one sample that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[19] in the JSON twin
  9. SumTreeArray · 63cadd6ee0a86ed0 · 2 bricks; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified · The assembly has not been run end-to-end · assemblies[20] in the JSON twin
  10. PrioritisedExperienceReplay · 6f88940f8576a2a5 · 1 brick; individually on a fixture: 1 ran (of which 1 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; the one sample that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[21] in the JSON twin
  11. Experience · 72ff215050535624 · 4 bricks; individually on a fixture: 3 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified · The assembly has not been run end-to-end · assemblies[22] in the JSON twin
  12. SumSegmentTree · 758216406e1b489c · 2 bricks; individually on a fixture: 2 ran (of which 2 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; every one of the 2 samples that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[23] in the JSON twin
  13. PrioritizedReplayBuffer · 840fb202302c8ebb · 10 bricks; individually on a fixture: 6 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; 2 where Syntology's instrument failed) · 4 unverified · The assembly has not been run end-to-end · assemblies[24] in the JSON twin
  14. PrioritizeBuffer · 879e143119e53b25 · 3 bricks; individually on a fixture: 2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified · The assembly has not been run end-to-end · assemblies[25] in the JSON twin
  15. ReplayMemory · 899dc9dfa74d974b · 1 brick; individually on a fixture: 0 ran · 1 unverified · The assembly has not been run end-to-end · assemblies[26] in the JSON twin
  16. PrioritizedReplayMemory · 8bfa4e34c2a4a5dd · 5 bricks; individually on a fixture: 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) · 1 unverified; every one of the 4 samples that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[27] in the JSON twin
  17. PrioritizedExperienceReplay · 9eb455c65e70b25f · 1 brick; individually on a fixture: 1 ran (of which 1 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; the one sample that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[28] in the JSON twin
  18. ReplayBuffer · a4ee78e1f8c360d8 · 1 brick; individually on a fixture: 0 ran · 1 unverified · The assembly has not been run end-to-end · assemblies[29] in the JSON twin
  19. ReplayBuffer · a9208093e5c9f0ae · 1 brick; individually on a fixture: 1 ran (of which 1 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; the one sample that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[30] in the JSON twin
  20. PERReplayMemory · a999e60299bf69c3 · 2 bricks; individually on a fixture: 2 ran (of which 2 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; every one of the 2 samples that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[31] in the JSON twin
  21. Agent · ac94b7a358686285 · 1 brick; individually on a fixture: 0 ran · 1 unverified · The assembly has not been run end-to-end · assemblies[32] in the JSON twin
  22. PrioritizedReplayMemory · aca95880c43840a4 · 3 bricks; individually on a fixture: 3 ran (of which 3 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) · 0 unverified; every one of the 3 samples that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[33] in the JSON twin
  23. LazyPrioritizedMultiStepMemory · b76fc53f0998fda1 · 7 bricks; individually on a fixture: 7 ran (of which 7 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) · 0 unverified; every one of the 7 samples that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[34] in the JSON twin
  24. ReplayBuffer · c0e2b164e64fb35d · 1 brick; individually on a fixture: 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 · The assembly has not been run end-to-end · assemblies[35] in the JSON twin
  25. ReplayBuffer · c74c2f5911a2e0ef · 1 brick; individually on a fixture: 0 ran · 1 unverified · The assembly has not been run end-to-end · assemblies[36] in the JSON twin
  26. SumTree · c869374e26f36137 · 1 brick; individually on a fixture: 1 ran (of which 1 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; the one sample that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[37] in the JSON twin
  27. ReplayMemory · ca434dbdb2b5228c · 1 brick; individually on a fixture: 0 ran · 1 unverified · The assembly has not been run end-to-end · assemblies[38] in the JSON twin
  28. ReplayBuffer · d071f3b9462ca123 · 2 bricks; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified · The assembly has not been run end-to-end · assemblies[39] in the JSON twin
  29. AgentMemory · d3fd457c99921e88 · 1 brick; individually on a fixture: 1 ran (of which 1 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; the one sample that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[40] in the JSON twin
  30. PrioritizedReplayBuffer · dffb47e4c7d12abc · 5 bricks; individually on a fixture: 3 ran (of which 3 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) · 2 unverified; every one of the 3 samples that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[41] in the JSON twin
  31. PriorityExperienceReplay · e78d3d85f5223174 · 3 bricks; individually on a fixture: 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 · The assembly has not been run end-to-end · assemblies[42] in the JSON twin
  32. PrioritizedReplayBuffer · ee9b213919d45f7a · 2 bricks; individually on a fixture: 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) · 1 unverified · The assembly has not been run end-to-end · assemblies[43] in the JSON twin
  33. ReplayMemory · fcb70b9f09d30ef8 · 1 brick; individually on a fixture: 0 ran · 1 unverified · The assembly has not been run end-to-end · assemblies[44] in the JSON twin

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="1511.05952") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Atari GamesReinforcement LearningReinforcement Learning (RL)reinforcement-learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Atari Games Atari 2600 Alien Prior noop Score 4203.8 #21 of 49 Archive leaderboard report
Atari Games Atari 2600 Alien Prior hs Score 1334.7 #35 of 49 Archive leaderboard report
Atari Games Atari 2600 Amidar Prior noop Score 1838.9 #12 of 48 Archive leaderboard report
Atari Games Atari 2600 Amidar Prior hs Score 129.1 #45 of 48 Archive leaderboard report
Atari Games Atari 2600 Assault Prior noop Score 7672.1 #22 of 45 Archive leaderboard report
Atari Games Atari 2600 Assault Prior hs Score 6548.9 #24 of 45 Archive leaderboard report
Atari Games Atari 2600 Asterix Prior noop Score 31527 #21 of 49 Archive leaderboard report
Atari Games Atari 2600 Asterix Prior hs Score 22484.5 #24 of 49 Archive leaderboard report
Atari Games Atari 2600 Asteroids Prior noop Score 2654.3 #23 of 43 Archive leaderboard report
Atari Games Atari 2600 Asteroids Prior hs Score 1745.1 #29 of 43 Archive leaderboard report
Atari Games Atari 2600 Atlantis Prior noop Score 357324.0 #30 of 42 Archive leaderboard report
Atari Games Atari 2600 Atlantis Prior hs Score 330647.0 #32 of 42 Archive leaderboard report
Atari Games Atari 2600 Bank Heist Prior noop Score 1054.6 #23 of 45 Archive leaderboard report
Atari Games Atari 2600 Bank Heist Prior hs Score 876.6 #31 of 45 Archive leaderboard report
Atari Games Atari 2600 Battle Zone Prior noop Score 31530.0 #23 of 47 Archive leaderboard report
Atari Games Atari 2600 Battle Zone Prior hs Score 25520.0 #31 of 47 Archive leaderboard report
Atari Games Atari 2600 Beam Rider Prior hs Score 31181.3 #13 of 49 Archive leaderboard report
Atari Games Atari 2600 Beam Rider Prior noop Score 23384.2 #18 of 49 Archive leaderboard report
Atari Games Atari 2600 Berzerk Prior noop Score 1305.6 #23 of 39 Archive leaderboard report
Atari Games Atari 2600 Berzerk Prior hs Score 865.9 #30 of 39 Archive leaderboard report
Atari Games Atari 2600 Bowling Prior hs Score 52 #29 of 44 Archive leaderboard report
Atari Games Atari 2600 Bowling Prior noop Score 47.9 #33 of 44 Archive leaderboard report
Atari Games Atari 2600 Boxing Prior noop Score 95.6 #24 of 45 Archive leaderboard report
Atari Games Atari 2600 Boxing Prior hs Score 72.3 #35 of 45 Archive leaderboard report
Atari Games Atari 2600 Breakout Prior noop Score 373.9 #29 of 58 Archive leaderboard report
Atari Games Atari 2600 Breakout Prior hs Score 343.0 #39 of 58 Archive leaderboard report
Atari Games Atari 2600 Centipede Prior noop Score 4463.2 #35 of 45 Archive leaderboard report
Atari Games Atari 2600 Centipede Prior hs Score 3489.1 #41 of 45 Archive leaderboard report
Atari Games Atari 2600 Chopper Command Prior noop Score 8600.0 #21 of 45 Archive leaderboard report
Atari Games Atari 2600 Chopper Command Prior hs Score 4635.0 #34 of 45 Archive leaderboard report
Atari Games Atari 2600 Crazy Climber Prior noop Score 141161.0 #19 of 49 Archive leaderboard report
Atari Games Atari 2600 Crazy Climber Prior hs Score 127512.0 #27 of 49 Archive leaderboard report
Atari Games Atari 2600 Demon Attack Prior noop Score 71846.4 #24 of 46 Archive leaderboard report
Atari Games Atari 2600 Demon Attack Prior hs Score 61277.5 #29 of 46 Archive leaderboard report
Atari Games Atari 2600 Double Dunk Prior noop Score 18.5 #13 of 43 Archive leaderboard report
Atari Games Atari 2600 Double Dunk Prior hs Score 16.0 #15 of 43 Archive leaderboard report
Atari Games Atari 2600 Enduro Prior noop Score 2093.0 #17 of 48 Archive leaderboard report
Atari Games Atari 2600 Enduro Prior hs Score 1831.0 #22 of 48 Archive leaderboard report
Atari Games Atari 2600 Fishing Derby Prior noop Score 39.5 #18 of 44 Archive leaderboard report
Atari Games Atari 2600 Fishing Derby Prior hs Score 9.8 #32 of 44 Archive leaderboard report
Atari Games Atari 2600 Freeway Prior noop Score 33.7 #14 of 59 Archive leaderboard report
Atari Games Atari 2600 Freeway Prior hs Score 28.9 #37 of 59 Archive leaderboard report
Atari Games Atari 2600 Frostbite Prior noop Score 4380.1 #18 of 53 Archive leaderboard report
Atari Games Atari 2600 Frostbite Prior hs Score 3510.0 #23 of 53 Archive leaderboard report
Atari Games Atari 2600 Gopher Prior hs Score 34858.8 #18 of 43 Archive leaderboard report
Atari Games Atari 2600 Gopher Prior noop Score 32487.2 #20 of 43 Archive leaderboard report
Atari Games Atari 2600 Gravitar Prior noop Score 548.5 #29 of 53 Archive leaderboard report
Atari Games Atari 2600 Gravitar Prior hs Score 269.5 #47 of 53 Archive leaderboard report
Atari Games Atari 2600 HERO Prior noop Score 23037.7 #22 of 44 Archive leaderboard report
Atari Games Atari 2600 HERO Prior hs Score 20889.9 #27 of 44 Archive leaderboard report
Atari Games Atari 2600 Ice Hockey Prior noop Score 1.3 #16 of 43 Archive leaderboard report
Atari Games Atari 2600 Ice Hockey Prior hs Score -0.2 #28 of 43 Archive leaderboard report
Atari Games Atari 2600 James Bond Prior noop Score 5148.0 #14 of 45 Archive leaderboard report
Atari Games Atari 2600 James Bond Prior hs Score 3961.0 #16 of 45 Archive leaderboard report
Atari Games Atari 2600 Kangaroo Prior noop Score 16200.0 #3 of 47 Archive leaderboard report
Atari Games Atari 2600 Kangaroo Prior hs Score 12185.0 #20 of 47 Archive leaderboard report
Atari Games Atari 2600 Krull Prior noop Score 9728.0 #21 of 45 Archive leaderboard report
Atari Games Atari 2600 Krull Prior hs Score 6872.8 #34 of 45 Archive leaderboard report
Atari Games Atari 2600 Kung-Fu Master Prior noop Score 39581.0 #22 of 43 Archive leaderboard report
Atari Games Atari 2600 Kung-Fu Master Prior hs Score 31676.0 #31 of 43 Archive leaderboard report
Atari Games Atari 2600 Montezuma's Revenge Prior hs Score 51 #33 of 50 Archive leaderboard report
Atari Games Atari 2600 Ms. Pacman Prior noop Score 6518.7 #13 of 47 Archive leaderboard report
Atari Games Atari 2600 Ms. Pacman Prior hs Score 1865.9 #35 of 47 Archive leaderboard report
Atari Games Atari 2600 Name This Game Prior noop Score 12270.5 #21 of 43 Archive leaderboard report
Atari Games Atari 2600 Name This Game Prior hs Score 10497.6 #29 of 43 Archive leaderboard report
Atari Games Atari 2600 Pong Prior noop Score 20.6 #24 of 52 Archive leaderboard report
Atari Games Atari 2600 Pong Prior hs Score 18.9 #37 of 52 Archive leaderboard report
Atari Games Atari 2600 Private Eye Prior hs Score 670.7 #24 of 52 Archive leaderboard report
Atari Games Atari 2600 Private Eye Prior noop Score 200.0 #36 of 52 Archive leaderboard report
Atari Games Atari 2600 Q*Bert Prior noop Score 16256.5 #23 of 57 Archive leaderboard report
Atari Games Atari 2600 Q*Bert Prior hs Score 9944 #40 of 57 Archive leaderboard report
Atari Games Atari 2600 River Raid Prior noop Score 14522.3 #21 of 41 Archive leaderboard report
Atari Games Atari 2600 River Raid Prior hs Score 11807.2 #26 of 41 Archive leaderboard report
Atari Games Atari 2600 Road Runner Prior noop Score 57608.0 #18 of 44 Archive leaderboard report
Atari Games Atari 2600 Road Runner Prior hs Score 52264.0 #25 of 44 Archive leaderboard report
Atari Games Atari 2600 Robotank Prior noop Score 62.6 #20 of 42 Archive leaderboard report
Atari Games Atari 2600 Robotank Prior hs Score 56.2 #27 of 42 Archive leaderboard report
Atari Games Atari 2600 Seaquest Prior noop Score 26357.8 #15 of 57 Archive leaderboard report
Atari Games Atari 2600 Seaquest Prior hs Score 25463.7 #16 of 57 Archive leaderboard report
Atari Games Atari 2600 Space Invaders Prior hs Score 3912.1 #23 of 55 Archive leaderboard report
Atari Games Atari 2600 Space Invaders Prior noop Score 2865.8 #29 of 55 Archive leaderboard report
Atari Games Atari 2600 Star Gunner Prior noop Score 63302.0 #24 of 43 Archive leaderboard report
Atari Games Atari 2600 Star Gunner Prior hs Score 61582.0 #25 of 43 Archive leaderboard report
Atari Games Atari 2600 Tennis Prior noop Score 0.0 #21 of 43 Archive leaderboard report
Atari Games Atari 2600 Tennis Prior hs Score -5.3 #34 of 43 Archive leaderboard report
Atari Games Atari 2600 Time Pilot Prior noop Score 9197.0 #24 of 44 Archive leaderboard report
Atari Games Atari 2600 Time Pilot Prior hs Score 5963.0 #33 of 44 Archive leaderboard report
Atari Games Atari 2600 Tutankham Prior noop Score 204.6 #24 of 44 Archive leaderboard report
Atari Games Atari 2600 Tutankham Prior hs Score 56.9 #40 of 44 Archive leaderboard report
Atari Games Atari 2600 Up and Down Prior noop Score 16154.1 #32 of 44 Archive leaderboard report
Atari Games Atari 2600 Up and Down Prior hs Score 12157.4 #36 of 44 Archive leaderboard report
Atari Games Atari 2600 Venture Prior hs Score 94.0 #33 of 55 Archive leaderboard report
Atari Games Atari 2600 Venture Prior noop Score 54.0 #36 of 55 Archive leaderboard report
Atari Games Atari 2600 Video Pinball Prior hs Score 295972.8 #24 of 42 Archive leaderboard report
Atari Games Atari 2600 Video Pinball Prior noop Score 282007.3 #25 of 42 Archive leaderboard report
Atari Games Atari 2600 Wizard of Wor Prior hs Score 5727.0 #30 of 41 Archive leaderboard report
Atari Games Atari 2600 Wizard of Wor Prior noop Score 4802.0 #32 of 41 Archive leaderboard report
Atari Games Atari 2600 Zaxxon Prior noop Score 10469.0 #25 of 41 Archive leaderboard report
Atari Games Atari 2600 Zaxxon Prior hs Score 9474.0 #28 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

Introduced by this paper: Prioritized Experience Replay

ConvolutionDQNDense ConnectionsExperience ReplayPrioritized Experience ReplayQ-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