Papers › Anti-Exploration by Random Network Distillation

Anti-Exploration by Random Network Distillation

31 Jan 2023arXiv:2301.13616archive 2025-07-28

Alexander Nikulin, Vladislav Kurenkov, Denis Tarasov, Sergey Kolesnikov

Despite the success of Random Network Distillation (RND) in various domains, it was shown as not discriminative enough to be used as an uncertainty estimator for penalizing out-of-distribution actions in offline reinforcement learning. In this paper, we revisit these results and show that, with a naive choice of conditioning for the RND prior, it becomes infeasible for the actor to effectively minimize the anti-exploration bonus and discriminativity is not an issue. We show that this limitation can be avoided with conditioning based on Feature-wise Linear Modulation (FiLM), resulting in a simple and efficient ensemble-free algorithm based on Soft Actor-Critic. We evaluate it on the D4RL benchmark, showing that it is capable of achieving performance comparable to ensemble-based methods and outperforming ensemble-free approaches by a wide margin.

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.

Syntology holds a reference implementation of Anti-Exploration by Random Network Distillation, generated from the paper text (not the authors' code), at level 3 on Syntology's ladder: V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” (quoted from Syntology's server card). No rung compares this code against the authors' implementation. For agents: get_reference_implementation(name='Anti-Exploration by Random Network Distillation') (how to connect); the free check have('2301.13616') needs no token.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 26 code samples harvested from 4 repositories linked to this paper: 20 ran (of which 18 constructed an object rather than computing a result; 19 with no instrument failure: 1 honoured, 0 violated, 18 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 18 samples from 1 repository, 17 ran (16 with no instrument failure; 1 where Syntology's instrument failed); community (archive-listed): 7 samples from 2 repositories, 3 ran (3 with no instrument failure; 0 where Syntology's instrument failed); community: 1 sample from 1 repository, 0 ran (0 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

tinkoff-ai/sac-rnd officialmentioned in papermentioned on GitHubjaxSyntology: 18 samples, 17 ran (1 instrument-failed) · 1 unverified report
zzmtsvv/sac_drnd mentioned on GitHubpytorchSyntology: 3 samples, 0 ran · 3 unverified report
zzmtsvv/sac_rnd mentioned on GitHubpytorchSyntology: 4 samples, 3 ran (0 instrument-failed) · 1 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

26 samples harvested: 20 ran (of which 18 constructed an object rather than computing a result; 19 with no instrument failure: 1 honoured, 0 violated, 18 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
1ran · our draft was wrong
18ran
6unverified

Licence: 7 of the 26 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 4 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 1 sample 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.

tinkoff-ai/sac-rnd official repository 18 samples, 17 ran (1 instrument-failed) · 1 unverified
BilinearDense offline_sac/networks.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · d69bcc085240a24a · report fixture: returned BilinearDense · level recorded 2026-09-22
BilinearFirstMLP offline_sac/networks.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 8f6f4cff35de62cf · report fixture: returned BilinearFirstMLP · level recorded 2026-09-22
BilinearFullMLP offline_sac/networks.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 0f917b109efda65c · report fixture: returned BilinearFullMLP · level recorded 2026-09-22
BilinearLastMLP offline_sac/networks.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · a231dfdd79465ac6 · report fixture: returned BilinearLastMLP · level recorded 2026-09-22
ConcatFirstMLP offline_sac/networks.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · bd41551ec9638504 · report fixture: returned ConcatFirstMLP · level recorded 2026-09-22
ConcatFullMLP offline_sac/networks.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 41028f940725e4a0 · report fixture: returned ConcatFullMLP · level recorded 2026-09-22
ConcatLastMLP offline_sac/networks.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 21b612feebc3499d · report fixture: returned ConcatLastMLP · level recorded 2026-09-22
FilmFirstMLP offline_sac/networks.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · be3f4b3f06b0e6bd · report fixture: returned FilmFirstMLP · level recorded 2026-09-22
FilmFullMLP offline_sac/networks.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 91e0406ad5665e10 · report fixture: returned FilmFullMLP · level recorded 2026-09-22
FilmLastMLP offline_sac/networks.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 3ea09b9fb948e867 · report fixture: returned FilmLastMLP · level recorded 2026-09-22
GatedMLP offline_sac/networks.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 12f4f05b82493956 · report fixture: returned GatedMLP · level recorded 2026-09-22
TorchBilinearDense offline_sac/networks.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · f08bbf7286cf9812 · report fixture: returned TorchBilinearDense · level recorded 2026-09-22
TorchBilinearFirstMLP offline_sac/networks.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 7131c9d471efe1a4 · report fixture: returned TorchBilinearFirstMLP · level recorded 2026-09-22
TorchBilinearFullMLP offline_sac/networks.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 93814161ebae72e3 · report fixture: returned TorchBilinearFullMLP · level recorded 2026-09-22
TorchBilinearLastMLP offline_sac/networks.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · a9a4771d15f5a324 · report fixture: returned TorchBilinearLastMLP · level recorded 2026-09-22
normalize in 638 papers
census: 70 implementations from 82 papers, 51 distinct outputs across 11 buckets, one shared input per bucket
offline_sac/networks.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · adb37ed22c2703a9 · report fixture: signature arr:ArrayImpl/2/float, mean:ArrayImpl/1/float, std:ArrayImpl/1/float, eps:float/0/float · returned ArrayImpl · level recorded 2026-09-22
pytorch_init offline_sac/networks.py ran · our draft was wrong Apache-2.0 (permissive) · b62cf8b42971d060 · report fixture: signature fan_in:float/0/float · returned function · level recorded 2026-09-22
RND in 5 papers offline_sac/networks.py unverified Apache-2.0 (permissive) · ffdc71693d91c600 · report
zzmtsvv/sac_drnd community (archive-listed) 3 samples, 0 ran · 3 unverified
DRND drnd_modules.py unverified no licence file found · pointer only · c901b83a37fd3070 · report
EnsembledFiLM drnd_modules.py unverified no licence file found · pointer only · 7120bed03164d5ad · report
EnsembledTargetNetwork drnd_modules.py unverified no licence file found · pointer only · bc04133ae453cf88 · report
zzmtsvv/sac_rnd community (archive-listed) 4 samples, 3 ran (0 instrument-failed) · 1 unverified
FiLM in 11 papers rnd_modules.py ran no licence file found · pointer only · ceefac1ae561a6c3 · report fixture: returned FiLM · level recorded 2026-09-22
PredictorNetwork rnd_modules.py ran no licence file found · pointer only · 590f9905be494072 · report fixture: returned PredictorNetwork · level recorded 2026-09-22
PriorNetwork rnd_modules.py ran no licence file found · pointer only · d33f9e805bac2d2e · report fixture: returned PriorNetwork · level recorded 2026-09-22
RND in 5 papers rnd_modules.py unverified no licence file found · pointer only · 28ed96e0bf8e9eab · report
shidilrzf/anti-exploration-rl community 1 sample, 0 ran · 1 unverified
train in 522 papers examples/train_ae.py unverified MIT (permissive) · 226a9594f55e107f · 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. For a generated assembly, an independent peer is a second implementation generated separately from the same paper text; neither implementation read the authors' code. At level 2 the two agreed numerically on the fixture's inputs; level 3 is recorded when property tests derived from the paper also passed on both, and each level 3 card prints how many its report lists. 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. A generated assembly's label was set when its code was generated for the method, and no model judged it; its card prints it as "by construction" or "not judged by a model". 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. Where an assembly's phrase has no constructed figure, a brick that ran is not among the harvested samples this build reads, and whether a brick's run only constructed an object is read from that brick's harvested sample, so the figure was not counted; it does not say there were none.

4 assemblies on this paper: 3 harvested, 1 generated, listed in 2 groups (siblings lifted in one batch form one group).

generated Assembly for Anti-Exploration by Random Network Distillation (graph method: Anti-Exploration by Random Network Distillation), generated from the paper text, not the repository's code. 1 brick; individually on a fixture: 1 ran (1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. Ran end-to-end against an independent peer (level 3; 5 property tests passed on both).

label matches by construction: the code was generated for this method (not judged by a model)

  1. compute_rnd_anti_exploration_bonus entry · level 3 · ran · honoured contract · 5be744d2d17a2841004557482134d623e95ec1273b3953987604f119736bd585

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

harvested Assembly for Anti-Exploration by Random Network Distillation (graph method: Anti-Exploration by Random Network Distillation). 18 bricks; individually on a fixture: 17 ran (of which 15 constructed an object rather than computing a result; 16 with no instrument failure: 1 honoured, 0 violated, 15 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 3 siblings

  1. RND entry · level 0 · unverified · ffdc71693d91c600
  2. normalize helper · level 1 · ran · honoured contract · adb37ed22c2703a9
  3. BilinearFirstMLP helper · level 1 · ran · 8f6f4cff35de62cf
  4. BilinearFullMLP helper · level 1 · ran · 0f917b109efda65c
  5. BilinearLastMLP helper · level 1 · ran · a231dfdd79465ac6
  6. ConcatFirstMLP helper · level 1 · ran · bd41551ec9638504
  7. ConcatFullMLP helper · level 1 · ran · 41028f940725e4a0
  8. ConcatLastMLP helper · level 1 · ran · 21b612feebc3499d
  9. FilmFirstMLP helper · level 1 · ran · be3f4b3f06b0e6bd
  10. FilmFullMLP helper · level 1 · ran · 91e0406ad5665e10
  11. FilmLastMLP helper · level 1 · ran · 3ea09b9fb948e867
  12. GatedMLP helper · level 1 · ran · 12f4f05b82493956
  13. TorchBilinearFirstMLP helper · level 1 · ran · 7131c9d471efe1a4
  14. TorchBilinearFullMLP helper · level 1 · ran · 93814161ebae72e3
  15. TorchBilinearLastMLP helper · level 1 · ran · a9a4771d15f5a324
  16. pytorch_init helper · level 1 · ran · our draft was wrong · b62cf8b42971d060
  17. BilinearDense helper · level 1 · ran · d69bcc085240a24a
  18. TorchBilinearDense helper · level 1 · ran · f08bbf7286cf9812

harvested Assembly for Anti-Exploration by Random Network Distillation (graph method: Anti-Exploration by Random Network Distillation). 4 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) · 1 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 3 siblings

  1. RND entry · level 0 · unverified · 28ed96e0bf8e9eab
  2. PredictorNetwork model · level 1 · ran · 590f9905be494072
  3. PriorNetwork model · level 1 · ran · d33f9e805bac2d2e
  4. FiLM helper · level 1 · ran · ceefac1ae561a6c3

harvested Assembly for Anti-Exploration by Random Network Distillation (graph method: Anti-Exploration by Random Network Distillation). 4 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) · 3 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 3 siblings

  1. DRND entry · level 0 · unverified · c901b83a37fd3070
  2. EnsembledTargetNetwork model · level 0 · unverified · bc04133ae453cf88
  3. PredictorNetwork model · level 1 · ran · 590f9905be494072
  4. EnsembledFiLM model · level 0 · unverified · 7120bed03164d5ad

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="2301.13616") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

D4RL

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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