SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2408.13567 · NeurIPS · 2024

Hybrid Training for Enhanced Multi-task Generalization in Multi-agent Reinforcement Learning

Mingliang Zhang, Sichang Su, Chengyang He, Guillaume Sartoretti

arXiv · PDF · Open in the Atlas

Code that ran

1 of 3 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 0 failures of our instrument; 2 no recorded run), measured 2026-11-22; 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/2408.13567.json · badge: /api/ran/2408.13567.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
Mr-Bright/HyGen community
Papers with Code archive
1 ran · 2 no recorded run
FunctionStatusWhere it lives
VDNMixer Ran
ran on a synthesized input
Mr-Bright/HyGen/src/learners/multi_task/hygen_learner.py
code served (permissive licence) · get_code("b1d551a21e69b991")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned Tensor, ndim 3, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 as th
import torch.nn as nn

class VDNMixer(nn.Module):

    def __init__(self):
        super(VDNMixer, self).__init__()

    def forward(self, agent_qs, batch, task=None):
        return th.sum(agent_qs, dim=2, keepdim=True)


INIT_ARGS = {}

ARGS = {
    'agent_qs': th.randn(2, 4, 3),
    'batch': {'state': th.randn(2, 8)},
    'task': None
}

if __name__ == '__main__':
    mixer = VDNMixer(**INIT_ARGS)
    output = mixer(**ARGS)
    print("Output shape:", output.shape)
    print("Output:", output)
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 3, dtype family float — no output shape is stated: observe_signature.py observed this class with its constructor sizes canonicalised where it could, which the node does not record, so its shape is not stated as this setup block's
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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
EpisodeBatch Not yet run
unverified (harvested, no recorded run)
Mr-Bright/HyGen/src/learners/multi_task/hygen_learner.py
code served (permissive licence) · get_code("0737faccab4dcfda")
How it ran

no invocation recorded.

HyGenLearner Not yet run
unverified (harvested, no recorded run)
Mr-Bright/HyGen/src/learners/multi_task/hygen_learner.py
code served (permissive licence) · get_code("0606c70a1a057aa0")
How it ran

no invocation recorded.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 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 3 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 2026-11-22.

Repositories linked to this paper

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

Abstract

In multi-agent reinforcement learning (MARL), achieving multi-task generalization to diverse agents and objectives presents significant challenges. Existing online MARL algorithms primarily focus on single-task performance, but their lack of multi-task generalization capabilities typically results in substantial computational waste and limited real-life applicability. Meanwhile, existing offline multi-task MARL approaches are heavily dependent on data quality, often resulting in poor performance on unseen tasks. In this paper, we introduce HyGen, a novel hybrid MARL framework, Hybrid Training for Enhanced Multi-Task Generalization, which integrates online and offline learning to ensure both multi-task generalization and training efficiency. Specifically, our framework extracts potential general skills from offline multi-task datasets. We then train policies to select the optimal skills under the centralized training and decentralized execution paradigm (CTDE). During this stage, we utilize a replay buffer that integrates both offline data and online interactions. We empirically demonstrate that our framework effectively extracts and refines general skills, yielding impressive generalization to unseen tasks. Comparative analyses on the StarCraft multi-agent challenge show that HyGen obtains superior performances across a broad range of tasks. Code is available at https://github.com/Mr-Bright/HyGen.

For agents

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

get_harvested_code_for_paper("2408.13567")
get_code_for_paper("2408.13567")
have("2408.13567")

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

curl https://syntology.ai/api/ran/2408.13567.json

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

[![Syntology run record](https://syntology.ai/api/ran/2408.13567.svg)](https://syntology.ai/paper/2408.13567)

Connect an agent — have() is free.