SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1709.06011 · 2017

Guided Deep Reinforcement Learning for Swarm Systems

arXiv · PDF · Open in the Atlas

Code that ran

3 of 4 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 0 have no contract verdict; 3 failures of our instrument; 1 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/1709.06011.json · badge: /api/ran/1709.06011.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
hex-plex/KiloBot-MultiAgent-RL reimplementation (classifier label)
classifier basis: classifier_2025
3 ran · 1 no recorded run
FunctionStatusWhere it lives
fetch_states_graph Ran
ran; our contract draft was wrong, not the code
hex-plex/KiloBot-MultiAgent-RL/model-train.py
code served (permissive licence) · get_code("916aa6d1edd1bc98")
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 tuple. 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 numpy as np
import torch
import torch.nn as nn

torch.manual_seed(0)

class Module(nn.Module):
    def __init__(self, state_dim):
        super().__init__()
        self.state_dim = state_dim
        self._state = np.random.randn(state_dim).astype(np.float32)
    
    def get_state(self):
        return self._state

class Env:
    def __init__(self, num_modules=3, state_dim=4):
        self.modules = [Module(state_dim) for _ in range(num_modules)]

observation = np.random.randn(2, 4).astype(np.float32)
info = {}
env = Env(num_modules=3, state_dim=4)

ARGS = {
    "observation": observation,
    "info": info,
    "env": env
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is 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
fetch_states_localize Ran
ran; our contract draft was wrong, not the code
hex-plex/KiloBot-MultiAgent-RL/model-train.py
code served (permissive licence) · get_code("573bad30e2eb8797")
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 tuple. 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 numpy as np

class MockModule:
    def __init__(self, state_size=3):
        self.state_size = state_size
    
    def get_state(self, normalized=False):
        return np.random.randn(self.state_size).astype(np.float32)

class MockEnv:
    def __init__(self):
        self.modules = [MockModule(state_size=5) for _ in range(2)]
        self.target = (100.0, 150.0)
        self.screen_width = 200
        self.screen_heigth = 300

observation = np.array([[1.5, 2.3, 3.1, 4.2]], dtype=np.float32)

info = {
    'localization_bit': np.array([0.8]),
    'target_distance': np.array([2.5]),
    'neighbouring_bit': np.array([0.3])
}

env = MockEnv()

ARGS = {
    'observation': observation,
    'info': info,
    'env': env
}
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 tuple — a tuple output has no array shape of its own; none is 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
fetch_states_localize Ran
ran; our contract draft was wrong, not the code
hex-plex/KiloBot-MultiAgent-RL/play-model.py
code served (permissive licence) · get_code("5bc08ac0fdda1114")
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 tuple. 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 numpy as np

class MockModule:
    def get_state(self, normalized=False):
        return np.array([0.1, 0.2, 0.3, 0.4], dtype=np.float32)

class MockEnv:
    def __init__(self):
        self.modules = [MockModule(), MockModule(), MockModule()]
        self.target = (100.0, 150.0)
        self.screen_width = 200.0
        self.screen_heigth = 300.0

observation = np.array([[1.0, 2.0, 3.0, 4.0], [5.0, 6.0, 7.0, 8.0]], dtype=np.float32)

info = {
    'localization_bit': np.array([[0.5], [0.6]], dtype=np.float32),
    'target_distance': np.array([[10.0], [20.0]], dtype=np.float32),
    'neighbouring_bit': np.array([[0.7], [0.8]], dtype=np.float32)
}

env = MockEnv()

ARGS = {
    'observation': observation,
    'info': info,
    'env': env
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is 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
preprocessReplayBuffer Not yet run
unverified (harvested, no recorded run)
hex-plex/KiloBot-MultiAgent-RL/model-train.py
code served (permissive licence) · get_code("6912dfe99280e57a")
How it ran

no invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 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 4 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 this paper, we investigate how to learn to control a group of cooperative agents with limited sensing capabilities such as robot swarms. The agents have only very basic sensor capabilities, yet in a group they can accomplish sophisticated tasks, such as distributed assembly or search and rescue tasks. Learning a policy for a group of agents is difficult due to distributed partial observability of the state. Here, we follow a guided approach where a critic has central access to the global state during learning, which simplifies the policy evaluation problem from a reinforcement learning point of view. For example, we can get the positions of all robots of the swarm using a camera image of a scene. This camera image is only available to the critic and not to the control policies of the robots. We follow an actor-critic approach, where the actors base their decisions only on locally sensed information. In contrast, the critic is learned based on the true global state. Our algorithm uses deep reinforcement learning to approximate both the Q-function and the policy. The performance of the algorithm is evaluated on two tasks with simple simulated 2D agents: 1) finding and maintaining a certain distance to each others and 2) locating a target.

For agents

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

get_harvested_code_for_paper("1709.06011")
get_code_for_paper("1709.06011")
have("1709.06011")

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

curl https://syntology.ai/api/ran/1709.06011.json

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

[![Syntology run record](https://syntology.ai/api/ran/1709.06011.svg)](https://syntology.ai/paper/1709.06011)

Connect an agent — have() is free.