SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2001.09212 · 2020

PCGRL: Procedural Content Generation via Reinforcement Learning

arXiv · PDF · Open in the Atlas

Code that ran

5 of 5 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 3 have 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/2001.09212.json · badge: /api/ran/2001.09212.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
amidos2006/gym-pcgrl canonical (classifier label)
classifier basis: census
3 ran · 0 no recorded run
copy not recorded community
not in the paper's declared repositories
2 ran · 0 no recorded run
FunctionStatusWhere it lives
get_floor_dist Ran
ran on a synthesized input
amidos2006/gym-pcgrl/gym_pcgrl/envs/helper.py
code served (permissive licence) · get_code("1a209a0529574115")
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 int, ndim 0, dtype family int, shape () 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 torch
import numpy as np

# Analyze the function: get_floor_dist takes a map (2D structure), fromTypes (collection of values),
# and floorTypes (collection of values). It iterates through the map checking if cells match fromTypes,
# then calculates distance to floorTypes using _calc_dist_floor.

# Create a small 2D map (list of lists)
# Map uses simple integer values to represent different tile types
map_data = [
    [0, 1, 2, 0],
    [1, 0, 0, 1],
    [2, 0, 1, 2],
    [0, 2, 0, 1]
]

# fromTypes: types that we search from (e.g., grass = 1)
fromTypes = [1]

# floorTypes: types that represent floor/ground we measure distance to (e.g., floor = 2)
floorTypes = [2]

ARGS = {
    "map": map_data,
    "fromTypes": fromTypes,
    "floorTypes": floorTypes
}
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 int, ndim 0, dtype family int, shape () — shape () 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
get_stats Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from smearle/control-pcgrl
pointer only · get_code("405a9f1e9dd6a316")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

get_tile_locations Ran
ran on a synthesized input
amidos2006/gym-pcgrl/gym_pcgrl/envs/helper.py
code served (permissive licence) · get_code("538a6377cf71941d")
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
import numpy as np

# Analyze the function:
# - map: expects indexing like map[y][x], returns values that are keys in a dict
# - tile_values: expects iterable of values that correspond to values in the map

# Create a simple 2D map (list of lists) with small integer tiles
map_data = [
    [0, 1, 0],
    [1, 2, 1],
    [0, 2, 0]
]

# Define the tile values that should be found in the map
tile_values = [0, 1, 2]

ARGS = {
    "map": map_data,
    "tile_values": tile_values
}
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 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
get_type_grouping Ran
ran on a synthesized input
amidos2006/gym-pcgrl/gym_pcgrl/envs/helper.py
code served (permissive licence) · get_code("1f551c6ddc6c9656")
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 int, ndim 0, dtype family int, shape () 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 torch
import numpy as np

# Construct a small 2D map with integer tile types
# Using a 4x3 map (width=4, height=3) with values representing different tile types
map_data = [
    [1, 2, 1, 2],
    [2, 1, 2, 1],
    [1, 1, 2, 2]
]

# Types to search for - looking for tiles with value 1
types = [1]

# Relative locations to check (neighbors: up, down, left, right, diagonals)
relLocs = [
    (-1, 0),  # left
    (1, 0),   # right
    (0, -1),  # up
    (0, 1),   # down
    (-1, -1), # up-left
    (1, -1),  # up-right
    (-1, 1),  # down-left
    (1, 1)    # down-right
]

# Min and max thresholds for grouping value
min_threshold = 1
max_threshold = 4

ARGS = {
    "map": map_data,
    "types": types,
    "relLocs": relLocs,
    "min": min_threshold,
    "max": max_threshold
}
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 int, ndim 0, dtype family int, shape () — shape () 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
tran_action Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
this paper's copy was not recorded; identical code first harvested from smearle/control-pcgrl
pointer only · get_code("2fd33ffbc4e17e54")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 5 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 5 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
get_floor_dist 1 other paper
1 later
2109.05489 (2021-09)
Illuminating Diverse Neural Cellular Automata for Level Generation
get_stats 1 other paper
1 later
2109.05489 (2021-09)
Illuminating Diverse Neural Cellular Automata for Level Generation
get_tile_locations 1 other paper
1 later
2109.05489 (2021-09)
Illuminating Diverse Neural Cellular Automata for Level Generation
get_type_grouping 1 other paper
1 later
2109.05489 (2021-09)
Illuminating Diverse Neural Cellular Automata for Level Generation
tran_action 1 other paper
1 later
2109.05489 (2021-09)
Illuminating Diverse Neural Cellular Automata for Level Generation

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

We investigate how reinforcement learning can be used to train level-designing agents. This represents a new approach to procedural content generation in games, where level design is framed as a game, and the content generator itself is learned. By seeing the design problem as a sequential task, we can use reinforcement learning to learn how to take the next action so that the expected final level quality is maximized. This approach can be used when few or no examples exist to train from, and the trained generator is very fast. We investigate three different ways of transforming two-dimensional level design problems into Markov decision processes and apply these to three game environments.

For agents

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

get_harvested_code_for_paper("2001.09212")
get_code_for_paper("2001.09212")
have("2001.09212")

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

curl https://syntology.ai/api/ran/2001.09212.json

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

[![Syntology run record](https://syntology.ai/api/ran/2001.09212.svg)](https://syntology.ai/paper/2001.09212)

Connect an agent — have() is free.