Papers › Effective Diversity in Population Based Reinforcement Learning

Effective Diversity in Population Based Reinforcement Learning

3 Feb 2020NeurIPS 2020 12arXiv:2002.00632archive 2025-07-28

Jack Parker-Holder, Aldo Pacchiano, Krzysztof Choromanski, Stephen Roberts

Exploration is a key problem in reinforcement learning, since agents can only learn from data they acquire in the environment. With that in mind, maintaining a population of agents is an attractive method, as it allows data be collected with a diverse set of behaviors. This behavioral diversity is often boosted via multi-objective loss functions. However, those approaches typically leverage mean field updates based on pairwise distances, which makes them susceptible to cycling behaviors and increased redundancy. In addition, explicitly boosting diversity often has a detrimental impact on optimizing already fruitful behaviors for rewards. As such, the reward-diversity trade off typically relies on heuristics. Finally, such methods require behavioral representations, often handcrafted and domain specific. In this paper, we introduce an approach to optimize all members of a population simultaneously. Rather than using pairwise distance, we measure the volume of the entire population in a behavioral manifold, defined by task-agnostic behavioral embeddings. In addition, our algorithm Diversity via Determinants (DvD), adapts the degree of diversity during training using online learning techniques. We introduce both evolutionary and gradient-based instantiations of DvD and show they effectively improve exploration without reducing performance when better exploration is not required.

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.

Syntology holds a reference implementation of Diversity via Determinants (DvD), 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='Diversity via Determinants (DvD)') (how to connect); the free check have('2002.00632') needs no token.

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

Code

Syntology 12 code samples harvested from 2 repositories linked to this paper: 10 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 2 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: official repository: 3 samples from 1 repository, 3 ran (1 with no instrument failure; 2 where Syntology's instrument failed); community (archive-listed): 9 samples from 1 repository, 7 ran (6 with no instrument failure; 1 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. 1 of the 10 samples that ran has no recorded date.

jparkerholder/DvD_ES officialmentioned in paperSyntology: 3 samples, 3 ran (2 instrument-failed) · 0 unverified report
holounic/DvD-TD3 mentioned on GitHubpytorchSyntology: 9 samples, 7 ran (1 instrument-failed) · 2 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

12 samples harvested: 10 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 2 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 · violated contract
2ran · our draft was wrong
1ran; the contract check could not run
6ran
2unverified

Licence: 9 of the 12 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 2 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.

jparkerholder/DvD_ES official repository 3 samples, 3 ran (2 instrument-failed) · 0 unverified
get_det es.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant Apache-2.0 (permissive) · 9f4ef0e29eb8bd25 · report fixture: signature pop:ndarray/2/float, params:dict/0/? · returned float64 · level recorded 2026-09-22
get_experiment experiments.py ran · our draft was wrong Apache-2.0 (permissive) · 808b1cbcf8ffbd49 · report fixture: signature params:dict/0/? · returned dict · level recorded, date not recorded
normalize2 es.py ran · violated contract fingerprinted Apache-2.0 (permissive) · 954aa28753459d3b · report fixture: signature data:ndarray/2/float, wrt:ndarray/2/float · returned ndarray · level recorded 2026-09-22
holounic/DvD-TD3 community (archive-listed) 9 samples, 7 ran (1 instrument-failed) · 2 unverified
Actor in 68 papers td3/algorithm.py ran fingerprinted no licence file found · pointer only · 01cff9d67cdcaecf · report fixture: returned Actor · level recorded 2026-09-22
BaseActorCritic td3/algorithm.py ran no licence file found · pointer only · 347f0fe517e50968 · report fixture: returned BaseActorCritic · level recorded 2026-09-22
Buffer in 23 papers td3/algorithm.py ran no licence file found · pointer only · aeecae3f15ea94c6 · report fixture: returned Buffer · level recorded 2026-09-22
Critic in 60 papers td3/algorithm.py ran no licence file found · pointer only · b97e9e0f24a99b33 · report fixture: returned Critic · level recorded 2026-09-22
DiversityLoss td3/algorithm.py ran fingerprinted no licence file found · pointer only · 71b8dc99038de04a · report fixture: returned DiversityLoss · level recorded 2026-09-22
TD3 td3/algorithm.py ran no licence file found · pointer only · ea4ac6af2af793cd · report fixture: returned TD3 · level recorded 2026-09-22
unpack_batch td3/algorithm.py ran · our draft was wrong fingerprinted no licence file found · pointer only · a72924a3e9838a33 · report fixture: signature batch:tuple/1/ndarray · returned tuple · level recorded 2026-09-22
DvDTD3 td3/algorithm.py unverified no licence file found · pointer only · 34d3b149455f4fee · report
soft_update in 8 papers td3/algorithm.py unverified no licence file found · pointer only · ea8c4add89ea88fb · 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.

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

generated Assembly for Diversity via Determinants (DvD) (graph method: Diversity via Determinants (DvD)), generated from the paper text, not the repository's code. 1 brick; individually on a fixture: 1 ran (0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 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_diversity_determinant entry · level 3 · ran; the contract check could not run · d06011c0ba93ed7c04a6f9b24f5f5e7b294a713dd578f8a7ea02d1fd055ff825

2 sibling assemblies for Diversity via Determinants (DvD) (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for Diversity via Determinants (DvD) (graph method: Diversity via Determinants (DvD)). 2 bricks; individually on a fixture: 2 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; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. get_det entry · level 1 · ran; the contract check could not run (RAISES) · 9f4ef0e29eb8bd25
  2. normalize2 helper · level 1 · ran · violated contract · 954aa28753459d3b

harvested Assembly for Diversity via Determinants (DvD) (graph method: Diversity via Determinants (DvD)). 9 bricks; individually on a fixture: 7 ran (of which 6 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. DvDTD3 entry · level 0 · unverified · 34d3b149455f4fee
  2. Buffer helper · level 1 · ran · aeecae3f15ea94c6
  3. Critic model · level 1 · ran · b97e9e0f24a99b33
  4. DiversityLoss loss · level 1 · ran · 71b8dc99038de04a
  5. TD3 model · level 1 · ran · ea4ac6af2af793cd
  6. unpack_batch helper · level 1 · ran · our draft was wrong · a72924a3e9838a33
  7. Actor model · level 1 · ran · 01cff9d67cdcaecf
  8. BaseActorCritic helper · level 1 · ran · 347f0fe517e50968
  9. soft_update helper · level 0 · unverified · ea8c4add89ea88fb

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="2002.00632") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

DiversityPoint ProcessesReinforcement LearningReinforcement Learning (RL)reinforcement-learning

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