Papers › Kaleidoscope: Learnable Masks for Heterogeneous Multi-agent Reinforcement Learning

Kaleidoscope: Learnable Masks for Heterogeneous Multi-agent Reinforcement Learning

11 Oct 2024arXiv:2410.08540archive 2025-07-28

Xinran Li, Ling Pan, Jun Zhang

In multi-agent reinforcement learning (MARL), parameter sharing is commonly employed to enhance sample efficiency. However, the popular approach of full parameter sharing often leads to homogeneous policies among agents, potentially limiting the performance benefits that could be derived from policy diversity. To address this critical limitation, we introduce Kaleidoscope, a novel adaptive partial parameter sharing scheme that fosters policy heterogeneity while still maintaining high sample efficiency. Specifically, Kaleidoscope maintains one set of common parameters alongside multiple sets of distinct, learnable masks for different agents, dictating the sharing of parameters. It promotes diversity among policy networks by encouraging discrepancy among these masks, without sacrificing the efficiencies of parameter sharing. This design allows Kaleidoscope to dynamically balance high sample efficiency with a broad policy representational capacity, effectively bridging the gap between full parameter sharing and non-parameter sharing across various environments. We further extend Kaleidoscope to critic ensembles in the context of actor-critic algorithms, which could help improve value estimations.Our empirical evaluations across extensive environments, including multi-agent particle environment, multi-agent MuJoCo and StarCraft multi-agent challenge v2, demonstrate the superior performance of Kaleidoscope compared with existing parameter sharing approaches, showcasing its potential for performance enhancement in MARL. The code is publicly available at https://github.com/LXXXXR/Kaleidoscope.

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 12 code samples harvested from 2 repositories linked to this paper: 11 ran (of which 2 constructed an object rather than computing a result; 6 with no instrument failure: 3 honoured, 0 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 9 samples from 1 repository, 8 ran (6 with no instrument failure; 2 where Syntology's instrument failed); community: 3 samples from 1 repository, 3 ran (0 with no instrument failure; 3 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 between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 3 of the 11 samples that ran have no recorded date.

lxxxxr/kaleidoscope officialmentioned in paperpytorchApache-2.0Syntology: 9 samples, 8 ran (2 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

12 samples harvested: 11 ran (of which 2 constructed an object rather than computing a result; 6 with no instrument failure: 3 honoured, 0 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · honoured contract
5ran · our draft was wrong
3ran
1unverified

Licence: 0 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”. “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.

lxxxxr/kaleidoscope official repository 9 samples, 8 ran (2 instrument-failed) · 1 unverified
KaleiLinear Kalei_MPE/src/modules/agents/rnn_agent.py ran Apache-2.0 (permissive) · 3e4047b55fdd8d46 · report fixture: returned KaleiLinear · level recorded 2026-09-22
compare_STE Kalei_MPE/src/modules/agents/rnn_agent.py ran Apache-2.0 (permissive) · d10c169fc33ec23c · report fixture: returned compare_STE · level recorded 2026-09-22
flatdim_box_multibinary Kalei_MPE/src/envs/gym_spaces_utils.py ran · honoured contract Apache-2.0 (permissive) · 35b9956a050d423d · report fixture: signature space:Box/2/float · returned int · level recorded 2026-09-24
flatdim_discrete Kalei_MPE/src/envs/gym_spaces_utils.py ran · honoured contract Apache-2.0 (permissive) · 33d389e8d257639f · report fixture: signature space:Discrete/0/int · returned int · level recorded 2026-09-24
gumbel_softmax_sample in 49 papers
census: 14 implementations from 16 papers, 4 distinct outputs on one shared input
Kalei_MPE/src/controllers/maddpg_controller.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 355d7b51c7ffd042 · report fixture: signature logits:Tensor/2/float, temperature:float/0/float · returned Tensor · level recorded 2026-09-24
onehot_from_logits in 10 papers Kalei_MPE/src/controllers/maddpg_controller.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 046b92243aae4f76 · report fixture: signature logits:Tensor/2/float, eps:float/0/float · returned Tensor · level recorded 2026-09-24
sample_gumbel in 62 papers Kalei_MPE/src/controllers/maddpg_controller.py ran Apache-2.0 (permissive) · 3695d66ab681cacf · report fixture: signature shape:tuple/1/int, eps:float/0/float, tens_type:tensortype/0/float · returned Tensor · level recorded 2026-09-24
work in 9 papers Kalei_MPE/src/search.py ran · honoured contract Apache-2.0 (permissive) · 930812c3b06fc858 · report fixture: signature cmd:str/0/str · returned int · level recorded 2026-09-22
Kalei_RNNAgent_1R3 Kalei_MPE/src/modules/agents/rnn_agent.py unverified Apache-2.0 (permissive) · 73ec7f831d9eb7bc · report
uoe-agents/epymarl community 3 samples, 3 ran (3 instrument-failed) · 0 unverified
extract_alg_name_from_config in 5 papers plot_results.py ran · our draft was wrong Apache-2.0 (permissive) · 868161eada09b424 · report fixture: signature config:dict/0/? · returned str · level recorded, date not recorded
extract_env_name_from_config in 5 papers plot_results.py ran · our draft was wrong Apache-2.0 (permissive) · b23d20b93b147852 · report fixture: signature config:dict/0/? · returned str · level recorded, date not recorded
load_results in 82 papers plot_results.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · e8a91a919b93f3e1 · report fixture: signature path:str/0/str, metric:str/0/str · returned defaultdict · level recorded, date not recorded

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.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for Kaleidoscope (graph method: Kaleidoscope). 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.

  1. Kalei_RNNAgent_1R3 entry · level 0 · unverified · 73ec7f831d9eb7bc
  2. KaleiLinear model · level 1 · ran · 3e4047b55fdd8d46
  3. compare_STE helper · level 1 · ran · d10c169fc33ec23c

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="2410.08540") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

DiversityMuJoCoMulti-agent Reinforcement LearningReinforcement LearningStarcraftreinforcement-learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

SET

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