SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1908.05567 · 2019

Deep reinforcement learning in World-Earth system models to discover sustainable management strategies

arXiv · PDF · Open in the Atlas

Code that ran

5 of 10 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 5 have no contract verdict; 0 failures of our instrument; 5 no recorded run), measured 2026-11-21; 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/1908.05567.json · badge: /api/ran/1908.05567.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
fstrnad/pyDRLinWESM canonical (classifier label)
classifier basis: census
5 ran · 5 no recorded run
FunctionStatusWhere it lives
get_management_parameter_dict Ran
ran on a synthesized input
fstrnad/pyDRLinWESM/AYS/ays_model.py
code served (permissive licence) · get_code("40e80ab6b711633f")
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 dict. 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 torch

torch.manual_seed(0)

# Test case 1: DEFAULT_NAME management
ARGS_1 = {
    'management': 'default',
    'all_parameters': {
        'param1': 10,
        'param2': 20,
        'param3': 30
    }
}

# Test case 2: degrowth management with matching parameters
ARGS_2 = {
    'management': 'degrowth',
    'all_parameters': {
        'param1': 10,
        'param2': 20,
        'param1_DG': 100,
        'param2_DG': 200
    }
}

# Test case 3: solar-radiation management
ARGS_3 = {
    'management': 'solar-radiation',
    'all_parameters': {
        'alpha': 5,
        'beta': 15,
        'alpha_SRM': 50,
        'beta_SRM': 150
    }
}

# Test case 4: energy-transformation management
ARGS_4 = {
    'management': 'energy-transformation',
    'all_parameters': {
        'efficiency': 0.8,
        'cost': 1000,
        'efficiency_ET': 0.95,
        'cost_ET': 800
    }
}

# Test case 5: carbon-capture-storage management
ARGS_5 = {
    'management': 'carbon-capture-storage',
    'all_parameters': {
        'capacity': 100,
        'rate': 0.5,
        'capacity_CCS': 500,
        'rate_CCS': 0.9
    }
}

# Use the first test case as the primary ARGS
ARGS = ARGS_1
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not 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
read_loss Ran
ran on a synthesized input
fstrnad/pyDRLinWESM/plots/learning_loss_analysis_functions.py
code served (permissive licence) · get_code("6c67b59c0c7c0bf0")
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 list, 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 pandas as pd
import tempfile
import os

# Create a temporary directory with test loss files
temp_dir = tempfile.mkdtemp()

# Create some sample loss files that match the expected format
for i in range(3):
    noise_strength = 0.0
    file_name = os.path.join(temp_dir, f'{i}_loss_function_noise{noise_strength:.2f}.txt')
    
    # Create a CSV file with steps and loss columns
    # Need at least episode_length rows (full_episode_length=8000 / 50 = 160)
    steps = list(range(200))
    loss_values = [0.5 - 0.001 * s for s in steps]
    
    df = pd.DataFrame({
        'steps': steps,
        'loss': loss_values
    })
    
    df.to_csv(file_name, sep=' ', header=False, index=False)

ARGS = {
    'file_path': temp_dir,
    'noise_strength': 0.0,
    'full_episode_length': 8000
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
pandas — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 3, dtype family float — a list output has no array shape of its own; none is stated
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
read_trajectories Ran
ran on a synthesized input
fstrnad/pyDRLinWESM/plots/learning_loss_analysis_functions.py
code served (permissive licence) · get_code("0d1e8ff72331134c")
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 list. 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 pandas as pd
import tempfile
import os

# Create a temporary directory with test trajectory files
tmpdir = tempfile.mkdtemp()

# Create some test trajectory files that match the expected format
noise_strength = 0.0
parameters = ['episodes', 'Survived steps', 'tested_survived_steps', 'Average reward', 'test_tot_reward']

# Create a few trajectory files with sufficient data
for i in range(3):
    file_name = os.path.join(tmpdir, f'{i}_survived_progress_noise{noise_strength:.2f}.txt')
    # Create a dataframe with enough rows (episode_length for full_episode_length=8000 is 80)
    data = {
        'episodes': list(range(100)),
        'Survived steps': [10 * j for j in range(100)],
        'tested_survived_steps': [5 * j for j in range(100)],
        'Average reward': [0.5 * j for j in range(100)],
        'test_tot_reward': [1.0 * j for j in range(100)]
    }
    df = pd.DataFrame(data)
    df.to_csv(file_name, sep=' ', header=False, index=False)

# Create one file with insufficient data (less than episode_length)
file_name = os.path.join(tmpdir, f'9_survived_progress_noise{noise_strength:.2f}.txt')
data = {
    'episodes': list(range(30)),
    'Survived steps': [10 * j for j in range(30)],
    'tested_survived_steps': [5 * j for j in range(30)],
    'Average reward': [0.5 * j for j in range(30)],
    'test_tot_reward': [1.0 * j for j in range(30)]
}
df = pd.DataFrame(data)
df.to_csv(file_name, sep=' ', header=False, index=False)

ARGS = {
    'file_path': tmpdir,
    'noise_strength': 0.0,
    'full_episode_length': 8000
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
pandas — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list — a list 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
rhs Ran
ran on a synthesized input
fstrnad/pyDRLinWESM/AYS/approach_jobst.py
code served (permissive licence) · get_code("9a3491c1b63a723a")
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 list, ndim 1, 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
import numpy as np

torch.manual_seed(0)

# Analyze the function signature and body
# rhs(AYS, t, a) where:
# - AYS: tuple/list of 3 values (A, Y, S) - unpacked as A, Y, S = AYS
# - t: time parameter (used but not directly in computation)
# - a: list/tuple with 2 boolean elements (a[0] for low growth, a[1] for energy transition)

# The function performs numerical operations on A, Y, S (scalars or arrays)
# and returns a list of 3 values

# Set up valid arguments
AYS = [1.0, 2.0, 3.0]  # A, Y, S as scalars
t = 0.0  # time parameter
a = [False, False]  # [low_growth_flag, energy_transition_flag]

ARGS = {
    "AYS": AYS,
    "t": t,
    "a": a
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
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
versioninfo2version Ran
ran on a synthesized input
fstrnad/pyDRLinWESM/AYS/ays_general.py
code served (permissive licence) · get_code("df056ce8ab73df8a")
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 str. 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 torch
import numpy as np

torch.manual_seed(0)

# versioninfo2version takes v_info and joins it as strings with '.'
# v_info should be an iterable of version components (int, str, etc.)

ARGS = {
    'v_info': (1, 2, 3, 4)
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not 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
AYS_rescaled_rhs Not yet run
unverified (harvested, no recorded run)
fstrnad/pyDRLinWESM/AYS/ays_model.py
code served (permissive licence) · get_code("b84f2f17f32df1d1")
How it ran

no invocation recorded.

AYS_sunny_PB Not yet run
unverified (harvested, no recorded run)
fstrnad/pyDRLinWESM/AYS/ays_model.py
code served (permissive licence) · get_code("f8c07d143d6f55aa")
How it ran

no invocation recorded.

compactification Not yet run
unverified (harvested, no recorded run)
fstrnad/pyDRLinWESM/AYS/ays_general.py
code served (permissive licence) · get_code("1d6b36e9b63cd4fa")
How it ran

no invocation recorded.

huber_loss Not yet run
unverified (harvested, no recorded run)
fstrnad/pyDRLinWESM/DeepReinforcementLearning/DQNNetworks.py
code served (permissive licence) · get_code("531264c237c944b4")
How it ran

no invocation recorded.

inv_compactification Not yet run
unverified (harvested, no recorded run)
fstrnad/pyDRLinWESM/AYS/AYS_Environment.py
code served (permissive licence) · get_code("794df851e12a4fe5")
How it ran

no invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 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 10 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 2026-11-21.

Repositories linked to this paper

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

Abstract

Increasingly complex, non-linear World-Earth system models are used for describing the dynamics of the biophysical Earth system and the socio-economic and socio-cultural World of human societies and their interactions. Identifying pathways towards a sustainable future in these models for informing policy makers and the wider public, e.g. pathways leading to a robust mitigation of dangerous anthropogenic climate change, is a challenging and widely investigated task in the field of climate research and broader Earth system science. This problem is particularly difficult when constraints on avoiding transgressions of planetary boundaries and social foundations need to be taken into account. In this work, we propose to combine recently developed machine learning techniques, namely deep reinforcement learning (DRL), with classical analysis of trajectories in the World-Earth system. Based on the concept of the agent-environment interface, we develop an agent that is generally able to act and learn in variable manageable environment models of the Earth system. We demonstrate the potential of our framework by applying DRL algorithms to two stylized World-Earth system models. Conceptually, we explore thereby the feasibility of finding novel global governance policies leading into a safe and just operating space constrained by certain planetary and socio-economic boundaries. The artificially intelligent agent learns that the timing of a specific mix of taxing carbon emissions and subsidies on renewables is of crucial relevance for finding World-Earth system trajectories that are sustainable on the long term.

For agents

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

get_harvested_code_for_paper("1908.05567")
get_code_for_paper("1908.05567")
have("1908.05567")

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

curl https://syntology.ai/api/ran/1908.05567.json

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

[![Syntology run record](https://syntology.ai/api/ran/1908.05567.svg)](https://syntology.ai/paper/1908.05567)

Connect an agent — have() is free.