Papers › Exploration by Random Network Distillation

Exploration by Random Network Distillation

30 Oct 2018ICLR 2019arXiv:1810.12894archive 2025-07-28

Yuri Burda, Harrison Edwards, Amos Storkey, Oleg Klimov

We introduce an exploration bonus for deep reinforcement learning methods that is easy to implement and adds minimal overhead to the computation performed. The bonus is the error of a neural network predicting features of the observations given by a fixed randomly initialized neural network. We also introduce a method to flexibly combine intrinsic and extrinsic rewards. We find that the random network distillation (RND) bonus combined with this increased flexibility enables significant progress on several hard exploration Atari games. In particular we establish state of the art performance on Montezuma's Revenge, a game famously difficult for deep reinforcement learning methods. To the best of our knowledge, this is the first method that achieves better than average human performance on this game without using demonstrations or having access to the underlying state of the game, and occasionally completes the first level.

PaperPDFConference PDFCodeCode 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

The archive's official repository (openai/random-network-distillation) was not harvested; the 43 samples below come from 14 community repositories.

Syntology 43 code samples harvested from 14 repositories linked to this paper: 31 ran (of which 12 constructed an object rather than computing a result; 24 with no instrument failure: 2 honoured, 1 violated, 21 with no contract checked; 7 where Syntology's instrument failed) · 12 unverified. Where Syntology's instrument failed: 6 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 43 samples from 14 repositories, 31 ran (24 with no instrument failure; 7 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

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

Levels written 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.

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

openai/random-network-distillation officialmentioned in papermentioned on GitHubtfSyntology: not harvested report
DuaneNielsen/rnd mentioned on GitHubpytorchSyntology: 5 samples, 4 ran (1 instrument-failed) · 1 unverified report
Francesco-Sovrano/Combining--experience-replay--with--exploration-by-random-network-distillation- mentioned on GitHubtfSyntology: 3 samples, 1 ran (1 instrument-failed) · 2 unverified report
Justkim/random-network-distillation-pytorch mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
LeejwUniverse/RL_Exploration_Pytorch mentioned on GitHubpytorchSyntology: not harvested report
Narsil/rl-baselines 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
alirezakazemipour/ppo-rnd mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
bacdavid/RND-O mentioned on GitHubSyntology: not harvested report
balloch/rl-exploration-transfer mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
forevergj/multithreading_ppo_RND mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
jakegrigsby/supersonic mentioned on GitHubtfSyntology: 2 samples, 1 ran (1 instrument-failed) · 1 unverified report
jcwleo/random-network-distillation-pytorch mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
jhare96/reinforcement-learning mentioned on GitHubtfSyntology: 10 samples, 5 ran (2 instrument-failed) · 5 unverified report
kngwyu/intrinsic-rewards mentioned on GitHubpytorchApache-2.0Syntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
lgerrets/rl18-curiosity mentioned on GitHubSyntology: not harvested report
michalnand/reinforcement_learning mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
microsoft/strategically_efficient_rl mentioned on GitHubtfMITSyntology: 5 samples, 4 ran (0 instrument-failed) · 1 unverified report
riveSunder/carle mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
riveSunder/moving_in_morley mentioned on GitHubpytorchMITSyntology: not harvested report
rle-foundation/rlexplore mentioned on GitHubjaxMITSyntology: not harvested report
uoe-agents/derl mentioned on GitHubpytorchSyntology: 6 samples, 4 ran (2 instrument-failed) · 2 unverified 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

43 samples harvested: 31 ran (of which 12 constructed an object rather than computing a result; 24 with no instrument failure: 2 honoured, 1 violated, 21 with no contract checked; 7 where Syntology's instrument failed) · 12 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · honoured contract
1ran · violated contract
6ran · our draft was wrong
1ran; the contract check could not run
21ran
12unverified

Licence: 16 of the 43 samples are pointer only, meaning Syntology does not serve that copy's text. For 1 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 14 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 2 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

DuaneNielsen/rnd community (archive-listed) 5 samples, 4 ran (1 instrument-failed) · 1 unverified
ActionEmbedding novelty_policy.py ran no licence file found · pointer only · 618895158b828fd1 · report fixture: returned ActionEmbedding · level recorded 2026-09-22
AtariNoveltyNet novelty_policy.py ran no licence file found · pointer only · ab2b5543eb73e12b · report fixture: returned AtariNoveltyNet · level recorded 2026-09-22
NoveltyPolicy novelty_policy.py ran no licence file found · pointer only · 4b17ba7e1f439380 · report fixture: returned NoveltyPolicy · level recorded 2026-09-22
conv_output_shape in 8 papers novelty_policy.py ran · our draft was wrong no licence file found · pointer only · 3212247a9c7830c7 · report fixture: signature h_w:tuple/1/int, kernel_size:int/0/int, stride:int/0/int, pad:int/0/int, dilation:int/0/int · returned tuple · level recorded 2026-09-22
Policy in 23 papers novelty_policy.py unverified no licence file found · pointer only · 920f08f608d008cb · report
Francesco-Sovrano/Combining--experience-replay--with--exploration-by-random-network-distillation- community (archive-listed) 3 samples, 1 ran (1 instrument-failed) · 2 unverified
orthogonal_initializer framework/agent/network/intrinsic_reward/intrinsic_reward_network.py ran · our draft was wrong MIT (permissive) · 7c704f729de99c78 · report fixture: signature scale:float/0/float · returned function · level recorded 2026-09-22
IntrinsicReward_Network framework/agent/network/intrinsic_reward/intrinsic_reward_network.py unverified MIT (permissive) · ebbe3600bbc2b502 · report
Network in 40 papers framework/agent/network/intrinsic_reward/intrinsic_reward_network.py unverified MIT (permissive) · f7540dc011b71e5d · report
Justkim/random-network-distillation-pytorch community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
TargetModel rnd_model.py ran no licence file found · pointer only · dcfcd26f3e5c57ad · report fixture: signature input_observations:Tensor/4/float · returned Tensor · level recorded 2026-09-24
alirezakazemipour/ppo-rnd community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
PredictorModel Brain/model.py ran · metamorphic tier: deterministic MIT (permissive) · ca383711596ca4f8 · report fixture: returned PredictorModel · level recorded 2026-09-22
conv_shape Brain/model.py ran · honoured contract fingerprinted MIT (permissive) · 7c4ff1e9e5bf27f4 · report fixture: signature input:int/0/int, kernel_size:int/0/int, stride:int/0/int, padding:int/0/int · returned int · level recorded 2026-09-22
balloch/rl-exploration-transfer community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
CnnEncoder rlexplore/rnd/rnd.py ran MIT (permissive) · cb9601f5aff84351 · report fixture: returned CnnEncoder · level recorded 2026-09-22
MlpEncoder rlexplore/rnd/rnd.py ran fingerprinted MIT (permissive) · 2c93ef20cabcc117 · report fixture: returned MlpEncoder · level recorded 2026-09-22
RND in 5 papers rlexplore/rnd/rnd.py ran MIT (permissive) · 7aa70f2869c53e71 · report fixture: returned RND · level recorded 2026-09-22
forevergj/multithreading_ppo_RND community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
RND in 5 papers brain_md.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · e654e54d98b9fc45 · report fixture: returned RND · level recorded 2026-09-22
jakegrigsby/supersonic community (archive-listed) 2 samples, 1 ran (1 instrument-failed) · 1 unverified
model in 13 papers supersonic/models.py ran · our draft was wrong no licence file found · pointer only · 4bd07d2275540030 · report fixture: signature model_id:str/0/str · returned function · level recorded 2026-09-22
ExplorationTarget supersonic/models.py unverified no licence file found · pointer only · edb8cf6be635e983 · report
jcwleo/random-network-distillation-pytorch community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
RNDModel model.py ran · metamorphic tier: deterministic MIT (permissive) · 8f69014b9b699054 · report fixture: signature next_obs:Tensor/4/float · returned tuple · level recorded 2026-09-22
jhare96/reinforcement-learning community (archive-listed) 10 samples, 5 ran (2 instrument-failed) · 5 unverified
ModelConfig in 12 papers rlib/RND/model.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 12f3d1927fc20cf0 · report fixture: returned ModelConfig · level recorded 2026-09-22
PPOConfig rlib/RND/model.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · a247afb083cad9ff · report fixture: returned PPOConfig · level recorded 2026-09-22
polynomial_sheduler rlib/RND/model.py ran · our draft was wrong Apache-2.0 (permissive) · a99332a9cc3b7293 · report fixture: signature optimiser:SGD/0/?, lr_final:float/0/float, decay_steps:int/0/int, power:float/0/float · returned LambdaLR · level recorded 2026-09-22
tonumpy rlib/RND/model.py ran · honoured contract Apache-2.0 (permissive) · ca8d4b1715a4e662 · report fixture: signature x:Tensor/2/float · returned ndarray · level recorded 2026-09-22
totorch in 5 papers rlib/RND/model.py ran · our draft was wrong Apache-2.0 (permissive) · 3ab1bc57b4217bc7 · report fixture: signature x:ndarray/2/float, device:str/0/str · returned Tensor · level recorded 2026-09-22
Agent in 42 papers rlib/RND/model.py unverified Apache-2.0 (permissive) · d1f045c24bd9b2b9 · report
PPOIntrinsic rlib/RND/model.py unverified Apache-2.0 (permissive) · 4fd2cec5b421371d · report
PPOModel rlib/RND/model.py unverified Apache-2.0 (permissive) · b748fd36e9fb6640 · report
RND in 5 papers rlib/RND/model.py unverified Apache-2.0 (permissive) · ed8d297030cd46b1 · report
totorch_many rlib/RND/model.py unverified Apache-2.0 (permissive) · 82f14c9f59ca7edc · report
kngwyu/intrinsic-rewards community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
rogue_config experiments/ppo_roguegym.py ran fingerprinted Apache-2.0 (permissive) · 8a7ed7f9726866e9 · report fixture: signature seed:int/0/int · returned dict · level recorded 2026-09-26
michalnand/reinforcement_learning community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
Model in 227 papers experiments/atari_easy/breakout/models/ppo_rnd/src/model_rnd.py ran MIT (permissive) · 1041ee8730b41597 · report fixture: returned Model · level recorded 2026-09-22
microsoft/strategically_efficient_rl community (archive-listed) 5 samples, 4 ran (0 instrument-failed) · 1 unverified
discount in 11 papers algorithms/agents/intrinsic.py ran fingerprinted MIT (permissive) here; the stored copy is pointer only · 0ca7ce32a4f2492c · report fixture: signature x:ndarray/1/float, gamma:float/0/float · returned ndarray · level recorded 2026-09-25
get_best_configs analyze_hyperparameters.py ran MIT (permissive) · b1c9a4762c24dd86 · report fixture: signature trials:dict/0/?, key:str/0/str, mode:str/0/str · returned list · level recorded 2026-09-26
load_last_checkpoint visualize_gym_atari.py ran MIT (permissive) · 779387c1139ff5c3 · report fixture: signature run:str/0/str, trainer_cls:callable/0/? · returned tuple · level recorded 2026-09-26
nash_conv train_multiagent.py ran MIT (permissive) · 4123e2d8163b9224 · report fixture: signature trainer:DummyTrainer/0/?, eval_workers:DummyEvalWorkers/0/? · returned dict · level recorded 2026-09-26
load_experiments plot_runs_csv.py unverified MIT (permissive) · 85c397ba249397f2 · report
riveSunder/carle community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
Motivator carle/mcl.py ran MIT (permissive) · 7e1ba7514a47399e · report fixture: signature action:Tensor/0/int · returned tuple · level recorded 2026-09-24
RND2D carle/mcl.py ran MIT (permissive) · 58bcd9d56221fa05 · report fixture: signature obs:Tensor/4/float · returned Tensor · level recorded 2026-09-24
uoe-agents/derl community (archive-listed) 6 samples, 4 ran (2 instrument-failed) · 2 unverified
RNDNetwork derl/intrinsic_rewards/rnd/rnd.py ran no licence file found · pointer only · be1c87bf6f5e3486 · report fixture: returned RNDNetwork · level recorded 2026-09-22
build_sequential derl/intrinsic_rewards/rnd/rnd.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 147627e47de141ae · report fixture: signature num_inputs:int/0/int, hiddens:list/1/int, activation:str/0/str, output_activation:bool/0/bool · returned Sequential · level recorded 2026-09-22
flatten in 178 papers
census: 4 implementations from 7 papers, 4 distinct outputs across 4 buckets, one shared input per bucket this sample: bucket 4 of 4, arg 1: rank 4, kind float, dtype float32
derl/intrinsic_rewards/rnd/rnd.py ran · our draft was wrong fingerprinted no licence file found · pointer only · df69c0a5d85d8bc3 · report fixture: signature tensor:Tensor/4/float · returned Tensor · level recorded 2026-09-22
prod in 40 papers derl/intrinsic_rewards/rnd/rnd.py ran · violated contract fingerprinted no licence file found · pointer only · 2fe739431c704a67 · report fixture: signature iterable:list/1/int · returned int · level recorded 2026-09-22
IntrinsicReward derl/intrinsic_rewards/rnd/rnd.py unverified no licence file found · pointer only · a04129b701562203 · report
RND in 5 papers derl/intrinsic_rewards/rnd/rnd.py unverified no licence file found · pointer only · 96d5517e9763275d · report

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.

12 assemblies on this paper: 12 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

12 sibling assemblies for Random Network Distillation (RND) (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for Random Network Distillation (RND) (graph method: Random Network Distillation (RND)). 10 bricks; individually on a fixture: 5 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified. The assembly has not been run end-to-end.

one of 12 siblings

  1. RND entry · level 0 · unverified · ed8d297030cd46b1
  2. Agent helper · level 0 · unverified · d1f045c24bd9b2b9
  3. PPOConfig helper · level 1 · ran · a247afb083cad9ff
  4. PPOIntrinsic model · level 0 · unverified · 4fd2cec5b421371d
  5. tonumpy helper · level 1 · ran · honoured contract · ca8d4b1715a4e662
  6. totorch_many helper · level 0 · unverified · 82f14c9f59ca7edc
  7. ModelConfig helper · level 1 · ran · 12f3d1927fc20cf0
  8. polynomial_sheduler helper · level 1 · ran · our draft was wrong · a99332a9cc3b7293
  9. PPOModel helper · level 0 · unverified · b748fd36e9fb6640
  10. totorch helper · level 1 · ran · our draft was wrong · 3ab1bc57b4217bc7

harvested Assembly for Random Network Distillation (RND) (graph method: Random Network Distillation (RND)). 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 12 siblings

  1. RND entry · level 1 · ran · e654e54d98b9fc45

harvested Assembly for Random Network Distillation (RND) (graph method: Random Network Distillation (RND)). 2 bricks; individually on a fixture: 2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 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.

one of 12 siblings

  1. PredictorModel entry · level 1 · ran · ca383711596ca4f8
  2. conv_shape helper · level 1 · ran · honoured contract · 7c4ff1e9e5bf27f4

harvested Assembly for Random Network Distillation (RND) (graph method: Random Network Distillation (RND)). 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 12 siblings

  1. Model entry · level 1 · ran · 1041ee8730b41597

harvested Assembly for Random Network Distillation (RND) (graph method: Random Network Distillation (RND)). 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.

one of 12 siblings

  1. RND entry · level 1 · ran · 7aa70f2869c53e71
  2. CnnEncoder model · level 1 · ran · cb9601f5aff84351
  3. MlpEncoder model · level 1 · ran · 2c93ef20cabcc117

harvested Assembly for Random Network Distillation (RND) (graph method: Random Network Distillation (RND)). 8 bricks; individually on a fixture: 6 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

one of 12 siblings

  1. RND entry · level 0 · unverified · 96d5517e9763275d
  2. IntrinsicReward helper · level 0 · unverified · a04129b701562203
  3. RNDNetwork model · level 1 · ran · be1c87bf6f5e3486
  4. flatten helper · level 1 · ran · our draft was wrong · df69c0a5d85d8bc3
  5. build_sequential helper · level 1 · ran; the contract check could not run (RAISES) · 147627e47de141ae
  6. prod helper · level 1 · ran · violated contract · 2fe739431c704a67
  7. Flatten helper · level 1 · ran · dca1bdd65a0d90e0
  8. init helper · level 1 · ran · our draft was wrong · 9de355e93051e4ad

harvested Assembly for Random Network Distillation (RND) (graph method: Random Network Distillation (RND)). 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.

one of 12 siblings

  1. TargetModel entry · level 1 · ran · dcfcd26f3e5c57ad

harvested Assembly for Random Network Distillation (RND) (graph method: Random Network Distillation (RND)). 5 bricks; individually on a fixture: 4 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; 1 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 12 siblings

  1. NoveltyPolicy entry · level 1 · ran · 4b17ba7e1f439380
  2. ActionEmbedding helper · level 1 · ran · 618895158b828fd1
  3. AtariNoveltyNet model · level 1 · ran · ab2b5543eb73e12b
  4. Policy helper · level 0 · unverified · 920f08f608d008cb
  5. conv_output_shape helper · level 1 · ran · our draft was wrong · 3212247a9c7830c7

harvested Assembly for Random Network Distillation (RND) (graph method: Random Network Distillation (RND)). 3 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) · 2 unverified. The assembly has not been run end-to-end.

one of 12 siblings

  1. IntrinsicReward_Network entry · level 0 · unverified · ebbe3600bbc2b502
  2. Network helper · level 0 · unverified · f7540dc011b71e5d
  3. orthogonal_initializer helper · level 1 · ran · our draft was wrong · 7c704f729de99c78

harvested Assembly for Random Network Distillation (RND) (graph method: Random Network Distillation (RND)). 2 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) · 0 unverified. The assembly has not been run end-to-end.

one of 12 siblings

  1. RNDModel entry · level 1 · ran · 8f69014b9b699054
  2. Flatten helper · level 1 · ran · d45cd0dd13f0cbc5

harvested Assembly for Random Network Distillation (RND) (graph method: Random Network Distillation (RND)). 2 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) · 0 unverified. The assembly has not been run end-to-end.

one of 12 siblings

  1. RND2D entry · level 1 · ran · 58bcd9d56221fa05
  2. Motivator helper · level 1 · ran · 7e1ba7514a47399e

harvested Assembly for Random Network Distillation (RND) (graph method: Random Network Distillation (RND)). 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.

one of 12 siblings

  1. ExplorationTarget entry · level 0 · unverified · edb8cf6be635e983
  2. model helper · level 1 · ran · our draft was wrong · 4bd07d2275540030

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="1810.12894") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

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

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Atari Games Atari 2600 Gravitar RND Score 3906 #11 of 53 Archive leaderboard report
Atari Games Atari 2600 Montezuma's Revenge RND Score 8152 #5 of 50 Archive leaderboard report
Atari Games Atari 2600 Pitfall! RND Score -3 #20 of 23 Archive leaderboard report
Atari Games Atari 2600 Private Eye RND Score 8666 #11 of 52 Archive leaderboard report
Atari Games Atari 2600 Solaris RND Score 3282 #17 of 23 Archive leaderboard report
Atari Games Atari 2600 Venture RND Score 1859 #9 of 55 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections