SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2210.03022 · ICLR · 2023

Stateful active facilitator: Coordination and Environmental Heterogeneity in Cooperative Multi-Agent Reinforcement Learning

Yoshua Bengio, Michael Mozer, Anirudh Goyal, Nicolas Heess, Tianmin Shu, Vedant Shah, Dianbo Liu, Oussama Boussif, Cristian Meo

arXiv · PDF · Open in the Atlas

Code that ran

3 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; 2 failures of our instrument; 0 no recorded run), measured 2026-11-22; 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/2210.03022.json · badge: /api/ran/2210.03022.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
veds12/hecogrid canonical (classifier label)
classifier basis not recorded on the link
2 ran · 0 no recorded run
jaggbow/saf canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
layer_init Ran
ran; our contract draft was wrong, not the code
jaggbow/saf/src/policies/saf.py
pointer only (licence: NONE) · get_code("beb42d440ccf2925")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jaggbow/saf 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.

occlude_mask Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
veds12/hecogrid/hecogrid/agents.py
code served (permissive licence) · get_code("398664cabd311521")
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 (4, 3) 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
import numba

# Create a small grid for testing
# The function expects a 3D array where grid.shape[:2] gives (width, height)
# Let's create a 4x3x1 grid (width=4, height=3, channels=1)
grid = np.array([
    [[1], [0], [1]],
    [[0], [1], [0]],
    [[1], [1], [1]],
    [[0], [0], [1]]
], dtype=np.uint8)

# Agent position should be within the grid bounds
# agent_pos[0] should be < 4 (width), agent_pos[1] should be < 3 (height)
agent_pos = np.array([1, 1], dtype=np.int64)

ARGS = {
    "grid": grid,
    "agent_pos": agent_pos
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numba, 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 (4, 3) — shape (4, 3) 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
rotate_grid Ran
ran on a synthesized input
veds12/hecogrid/hecogrid/base.py
code served (permissive licence) · get_code("04e15c2dc16b7768")
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 int, shape (3, 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 a small test grid (2D array)
grid = np.arange(12).reshape(4, 3)

# Create rotation parameter
rot_k = 1

ARGS = {
    "grid": grid,
    "rot_k": rot_k,
}
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 int, shape (3, 4) — shape (3, 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

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, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 3 later) and 0 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.

FunctionAlso present inEarliest-datedOthers named
layer_init 28 other papers
7 dated earlier, 20 later, 1 undated · 2 only as an assembly brick
1611.02779 (2016-11)
RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning
1611.05763 (2016-11)
Learning to reinforcement learn
1703.03400 (2017-03)
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
and 25 more not named here
occlude_mask 2 other papers
1 dated earlier, 1 later
2010.00581 (2020-10)
Emergent Social Learning via Multi-agent Reinforcement Learning
aaai_26923 (2023 (year only))
Theory of Mind: A Familiar Aspect of Humanity to Give Machines
rotate_grid 2 other papers
1 dated earlier, 1 later
2010.00581 (2020-10)
Emergent Social Learning via Multi-agent Reinforcement Learning
aaai_26923 (2023 (year only))
Theory of Mind: A Familiar Aspect of Humanity to Give Machines

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 cooperative multi-agent reinforcement learning, a team of agents works together to achieve a common goal. Different environments or tasks may require varying degrees of coordination among agents in order to achieve the goal in an optimal way. The nature of coordination will depend on the properties of the environmentits spatial layout, distribution of obstacles, dynamics, etc. We term this variation of properties within an environment as heterogeneity. Existing literature has not sufficiently addressed the fact that different environments may have different levels of heterogeneity. We formalize the notions of coordination level and heterogeneity level of an environment and present HECOGrid, a suite of multi-agent RL environments that facilitates empirical evaluation of different MARL approaches across different levels of coordination and environmental heterogeneity by providing a quantitative control over coordination and heterogeneity levels of the environment. Further, we propose a Centralized Training Decentralized Execution learning approach called Stateful Active Facilitator (SAF) that enables agents to work efficiently in high-coordination and high-heterogeneity environments through a differentiable and shared knowledge source used during training and dynamic selection from a shared pool of policies. We evaluate SAF and compare its performance against baselines IPPO and MAPPO on HECOGrid. Our results show that SAF consistently outperforms the baselines across different tasks and different heterogeneity and coordination levels. We release the code for HECOGrid 1 as well as all our experiments.

For agents

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

get_harvested_code_for_paper("2210.03022")
get_code_for_paper("2210.03022")
have("2210.03022")

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

curl https://syntology.ai/api/ran/2210.03022.json

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

[![Syntology run record](https://syntology.ai/api/ran/2210.03022.svg)](https://syntology.ai/paper/2210.03022)

Connect an agent — have() is free.