Papers › Settling Decentralized Multi-Agent Coordinated Exploration by Novelty Sharing

Settling Decentralized Multi-Agent Coordinated Exploration by Novelty Sharing

3 Feb 2024arXiv:2402.02097archive 2025-07-28

Haobin Jiang, Ziluo Ding, Zongqing Lu

Exploration in decentralized cooperative multi-agent reinforcement learning faces two challenges. One is that the novelty of global states is unavailable, while the novelty of local observations is biased. The other is how agents can explore in a coordinated way. To address these challenges, we propose MACE, a simple yet effective multi-agent coordinated exploration method. By communicating only local novelty, agents can take into account other agents' local novelty to approximate the global novelty. Further, we newly introduce weighted mutual information to measure the influence of one agent's action on other agents' accumulated novelty. We convert it as an intrinsic reward in hindsight to encourage agents to exert more influence on other agents' exploration and boost coordinated exploration. Empirically, we show that MACE achieves superior performance in three multi-agent environments with sparse rewards.

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 18 code samples: 17 from 1 repository linked to this paper, 1 identical to code harvested from another paper's repository. Across all 18: 16 ran (of which 12 constructed an object rather than computing a result; 15 with no instrument failure: 3 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 2 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: 17 samples from 1 repository, 15 ran (15 with no instrument failure; 0 where Syntology's instrument failed); 1 identical to code first harvested elsewhere. 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.

sigmabm/mace officialmentioned in papermentioned on GitHubpytorchSyntology: 17 samples, 15 ran (0 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

18 samples harvested: 16 ran (of which 12 constructed an object rather than computing a result; 15 with no instrument failure: 3 honoured, 0 violated, 12 with no contract checked; 1 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.

3ran · honoured contract
1ran · our draft was wrong
12ran
2unverified

Licence: 18 of the 18 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 sigmabm/mace. 1 sample is listed last, in a group without a repository. “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 9 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.

sigmabm/mace official repository 17 samples, 15 ran (0 instrument-failed) · 2 unverified
ACTLayer src/algo/r_mappo/hdd_net.py ran · metamorphic tier: deterministic no licence file found · pointer only · 56f9da3f7c1a4f65 · report fixture: returned ACTLayer · level recorded 2026-09-22
AddBias src/algo/r_mappo/hdd_net.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 6ea7d9f4a4c4f42d · report fixture: returned AddBias · level recorded 2026-09-22
Bernoulli in 7 papers src/algo/r_mappo/hdd_net.py ran · metamorphic tier: deterministic no licence file found · pointer only · e59c1d4221cf2cc6 · report fixture: returned Bernoulli · level recorded 2026-09-22
CNNBase src/algo/r_mappo/hdd_net.py ran · metamorphic tier: deterministic no licence file found · pointer only · 44f09ebd8f4371fa · report fixture: returned CNNBase · level recorded 2026-09-22
CNNLayer src/algo/r_mappo/hdd_net.py ran · metamorphic tier: deterministic no licence file found · pointer only · 605e1876fb9959d1 · report fixture: returned CNNLayer · level recorded 2026-09-22
Categorical in 6 papers src/algo/r_mappo/hdd_net.py ran · metamorphic tier: deterministic no licence file found · pointer only · 7e51bfa5785fa3e2 · report fixture: returned Categorical · level recorded 2026-09-22
DiagGaussian src/algo/r_mappo/hdd_net.py ran · metamorphic tier: deterministic no licence file found · pointer only · 4a0bedc273a7976f · report fixture: returned DiagGaussian · level recorded 2026-09-22
FixedBernoulli src/algo/r_mappo/hdd_net.py ran · metamorphic tier: deterministic no licence file found · pointer only · c5e85256674b40f2 · report fixture: returned FixedBernoulli · level recorded 2026-09-22
FixedCategorical src/algo/r_mappo/hdd_net.py ran · metamorphic tier: deterministic no licence file found · pointer only · 16be22c531bda7dd · report fixture: returned FixedCategorical · level recorded 2026-09-22
FixedNormal src/algo/r_mappo/hdd_net.py ran · metamorphic tier: deterministic no licence file found · pointer only · 3e39c2c0ee8e9467 · report fixture: returned FixedNormal · level recorded 2026-09-22
MLPBase src/algo/r_mappo/hdd_net.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 7071cd9f15e235a6 · report fixture: returned MLPBase · level recorded 2026-09-22
MLPLayer in 15 papers src/algo/r_mappo/hdd_net.py ran · metamorphic tier: deterministic no licence file found · pointer only · 235b02a593e7a345 · report fixture: returned MLPLayer · level recorded 2026-09-22
check in 38 papers
census: 5 implementations from 6 papers, 4 distinct outputs across 4 buckets, one shared input per bucket this sample: bucket 1 of 4, arg 1: rank 2, kind float, dtype float32
src/algo/r_mappo/hdd_net.py ran · honoured contract no licence file found · pointer only · 4829105008c71d83 · report fixture: signature input:ndarray/2/float · returned Tensor · level recorded 2026-09-22
get_grad_norm in 45 papers src/algo/r_mappo/hdd_net.py ran · honoured contract no licence file found · pointer only · 6b68682cdb55cf2a · report fixture: signature it:generator/0/? · returned float · level recorded 2026-09-22
get_shape_from_obs_space src/algo/r_mappo/hdd_net.py ran · honoured contract no licence file found · pointer only · 54fb8bdc67bc3d35 · report fixture: signature obs_space:Box/2/float · returned tuple · level recorded 2026-09-22
HDD src/algo/r_mappo/hdd_net.py unverified no licence file found · pointer only · 8834bcc7821f03a0 · report
HDDNetworks src/algo/r_mappo/hdd_net.py unverified no licence file found · pointer only · 11b84e10130bc082 · report
Repository not located 1 sample, 1 ran (1 instrument-failed) · 0 unverified
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
init in 55 papers repository not located ran · our draft was wrong licence of this copy not recorded · 9de355e93051e4ad · report fixture: signature module:callable/0/?, weight_init:callable/0/?, bias_init:callable/0/?, gain:int/0/int · returned Linear · level recorded 2026-09-22

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 MACE (graph method: MACE). 20 bricks; individually on a fixture: 18 ran (of which 12 constructed an object rather than computing a result; 16 with no instrument failure: 3 honoured, 0 violated, 13 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

  1. HDDNetworks entry · level 0 · unverified · 11b84e10130bc082
  2. HDD model · level 0 · unverified · 8834bcc7821f03a0
  3. check helper · level 1 · ran · honoured contract · 4829105008c71d83
  4. get_grad_norm helper · level 1 · ran · honoured contract · 6b68682cdb55cf2a
  5. ACTLayer helper · level 1 · ran · 56f9da3f7c1a4f65
  6. CNNBase helper · level 1 · ran · 44f09ebd8f4371fa
  7. MLPBase helper · level 1 · ran · 7071cd9f15e235a6
  8. get_shape_from_obs_space helper · level 1 · ran · honoured contract · 54fb8bdc67bc3d35
  9. Bernoulli helper · level 1 · ran · e59c1d4221cf2cc6
  10. Categorical helper · level 1 · ran · 7e51bfa5785fa3e2
  11. DiagGaussian helper · level 1 · ran · 4a0bedc273a7976f
  12. CNNLayer helper · level 1 · ran · 605e1876fb9959d1
  13. MLPLayer helper · level 1 · ran · 235b02a593e7a345
  14. FixedBernoulli helper · level 1 · ran · c5e85256674b40f2
  15. init helper · level 1 · ran · our draft was wrong · 9de355e93051e4ad
  16. FixedCategorical helper · level 1 · ran · 16be22c531bda7dd
  17. AddBias helper · level 1 · ran · 6ea7d9f4a4c4f42d
  18. FixedNormal helper · level 1 · ran · 3e39c2c0ee8e9467
  19. Flatten helper · level 1 · ran · dca1bdd65a0d90e0
  20. get_clones helper · level 1 · ran · our draft was wrong · 891b8ebab395921f

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="2402.02097") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Multi-agent 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