SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2002.00632 · NeurIPS · 2020

Effective Diversity in Population Based Reinforcement Learning

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

arXiv · PDF · Open in the Atlas

Code that ran

10 of 12 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (6 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 1 violated it and 6 have no contract verdict; 3 failures of our instrument; 2 no recorded run), measured 2026-11-21; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2002.00632.json · badge: /api/ran/2002.00632.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
jparkerholder/DvD_ES canonical (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
holounic/DvD-TD3 community
Papers with Code archive
7 ran · 2 no recorded run
FunctionStatusWhere it lives
Actor Ran
ran on a synthesized input · constructed an object; no result was computed
holounic/DvD-TD3/td3/algorithm.py
pointer only (licence: NONE) · get_code("01cff9d67cdcaecf")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, holounic/DvD-TD3 when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

BaseActorCritic Ran
ran on a synthesized input · constructed an object; no result was computed
holounic/DvD-TD3/td3/algorithm.py
pointer only (licence: NONE) · get_code("347f0fe517e50968")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, holounic/DvD-TD3 when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Buffer Ran
ran on a synthesized input · constructed an object; no result was computed
holounic/DvD-TD3/td3/algorithm.py
pointer only (licence: NONE) · get_code("aeecae3f15ea94c6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, holounic/DvD-TD3 when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Critic Ran
ran on a synthesized input · constructed an object; no result was computed
holounic/DvD-TD3/td3/algorithm.py
pointer only (licence: NONE) · get_code("b97e9e0f24a99b33")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, holounic/DvD-TD3 when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

DiversityLoss Ran
ran on a synthesized input · constructed an object; no result was computed
holounic/DvD-TD3/td3/algorithm.py
pointer only (licence: NONE) · get_code("71b8dc99038de04a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, holounic/DvD-TD3 when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

TD3 Ran
ran on a synthesized input · constructed an object; no result was computed
holounic/DvD-TD3/td3/algorithm.py
pointer only (licence: NONE) · get_code("ea4ac6af2af793cd")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, holounic/DvD-TD3 when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_det Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
jparkerholder/DvD_ES/es.py
code served (permissive licence) · get_code("9f4ef0e29eb8bd25")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned float64, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np
from sklearn.metrics.pairwise import rbf_kernel, linear_kernel
from sklearn.gaussian_process.kernels import Matern, RationalQuadratic

# Set random seed for reproducibility
np.random.seed(0)

# Create a small population matrix (5 samples, 3 features)
pop = np.random.randn(5, 3).astype(np.float64)

# Create a params dict with a valid dpp_kernel choice
params = {
    'dpp_kernel': 'Matern5'
}

ARGS = {
    'pop': pop,
    'params': params
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, sklearn — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float64, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_experiment Ran
ran; our contract draft was wrong, not the code
jparkerholder/DvD_ES/experiments.py
code served (permissive licence) · get_code("808b1cbcf8ffbd49")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned dict. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# The function takes a params dict and modifies it based on env_name
# It returns the modified params dict
# No complex objects are needed - just a dictionary with 'env_name' key

ARGS = {
    'params': {
        'env_name': 'HalfCheetah-v2'
    }
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
normalize2 Ran
ran, violated the contract we drafted
jparkerholder/DvD_ES/es.py
code served (permissive licence) · get_code("954aa28753459d3b")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# Create sample data arrays
# data: the array to normalize
# wrt: the reference array to compute min/max from
data = np.array([[1.0, 2.0, 3.0, 4.0],
                 [5.0, 6.0, 7.0, 8.0]])

wrt = np.array([[0.0, 1.0, 2.0, 3.0],
                [10.0, 11.0, 12.0, 13.0]])

ARGS = {
    "data": data,
    "wrt": wrt,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
unpack_batch Ran
ran; our contract draft was wrong, not the code
holounic/DvD-TD3/td3/algorithm.py
pointer only (licence: NONE) · get_code("a72924a3e9838a33")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, holounic/DvD-TD3 when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

DvDTD3 Not yet run
unverified (harvested, no recorded run)
holounic/DvD-TD3/td3/algorithm.py
pointer only (licence: NONE) · get_code("34d3b149455f4fee")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, holounic/DvD-TD3 when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

soft_update Not yet run
unverified (harvested, no recorded run)
holounic/DvD-TD3/td3/algorithm.py
pointer only (licence: NONE) · get_code("ea8c4add89ea88fb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, holounic/DvD-TD3 when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 12 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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 multiobjective 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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2002.00632")
get_code_for_paper("2002.00632")
have("2002.00632")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2002.00632.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2002.00632.svg)](https://syntology.ai/paper/2002.00632)

Connect an agent — have() is free.