SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2107.06405 · ICML · 2021

Shortest-Path Constrained Reinforcement Learning for Sparse Reward Tasks

Sungryull Sohn, Jongwook Choi, Honglak Lee, Harm Van Seijen, Mehdi Fatemi, Sungtae Lee

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; 1 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 1 failure of our instrument; 0 no recorded run); 1 of them was also run on the host, not in the jail, by the peer-agreement lane that set its level, 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/2107.06405.json · badge: /api/ran/2107.06405.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
srsohn/shortest-path-rl canonical (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
FunctionStatusWhere it lives
flatten_list Ran
ran, honoured the contract we drafted
srsohn/shortest-path-rl/scripts/launcher_script.py
code served (permissive licence) · get_code("41e9eb8faeb69064")
How it ran

Ran in Syntology's jail on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned list, ndim 1, dtype family int; no output shape is stated. The image it ran in was not recorded. The comparison behind this sample's level is a different run: the peer-agreement lane ran it again on the host, not in the jail (report dated 2026-09-04T23:29:20Z). 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)

# The function flatten_list takes a list of lists and flattens it
# It iterates through each sublist and yields each item

# Create a simple nested list structure
to_flatten = [
    [1, 2, 3],
    [4, 5],
    [6, 7, 8, 9]
]

ARGS = {
    "to_flatten": to_flatten
}
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 list, ndim 1, dtype family int — 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
assemble_command Ran
ran; our contract draft was wrong, not the code
srsohn/shortest-path-rl/scripts/launcher_script.py
code served (permissive licence) · get_code("e7087fd5c20b09f0")
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 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 six

def flatten_list(to_flatten):
    return [item for sublist in to_flatten for item in sublist]

def quote_gin_value(v):
    if isinstance(v, six.string_types):
        return '"{}"'.format(v)
    return v

def assemble_command(base_command, params):
    """Builds a command line to launch training.

  Args:
    base_command: list(str), command prefix.
    params: dict of param -> value. Parameters prefixed by '_gin.' are
      considered gin parameters.

  Returns:
    List of strings, the components of the command line to run.
  """
    gin_params = {param_name: param_value for param_name, param_value in params.items() if param_name.startswith('_gin.')}
    params = {param_name: param_value for param_name, param_value in params.items() if not param_name.startswith('_gin.')}
    return base_command + ['--{}={}'.format(param, v) for param, v in params.items()] + flatten_list([['--gin_bindings', '{}={}'.format(gin_param[len('_gin.'):], quote_gin_value(v))] for gin_param, v in gin_params.items()])


ARGS = {
    'base_command': ['python', 'train.py'],
    'params': {
        'learning_rate': 0.001,
        'batch_size': 32,
        'epochs': 10,
        '_gin.model.hidden_size': 256,
        '_gin.optimizer.beta1': 0.9,
        '_gin.dataset.name': 'cifar10'
    }
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
six — 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
quote_gin_value Ran
ran, violated the contract we drafted
srsohn/shortest-path-rl/scripts/launcher_script.py
code served (permissive licence) · get_code("18c219550ff9bc1f")
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 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 six

ARGS = {
    "v": "test_string"
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
six — 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

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

We propose the k-Shortest-Path (k-SP) constraint: a novel constraint on the agent's trajectory that improves the sample efficiency in sparse-reward MDPs. We show that any optimal policy necessarily satisfies the k-SP constraint. Notably, the k-SP constraint prevents the policy from exploring state-action pairs along the non-k-SP trajectories (e.g., going back and forth). However, in practice, excluding state-action pairs may hinder the convergence of RL algorithms. To overcome this, we propose a novel cost function that penalizes the policy violating SP constraint, instead of completely excluding it. Our numerical experiment in a tabular RL setting demonstrates that the SP constraint can significantly reduce the trajectory space of policy. As a result, our constraint enables more sample efficient learning by suppressing redundant exploration and exploitation. Our experiments on MiniGrid, DeepMind Lab, Atari, and Fetch show that the proposed method significantly improves proximal policy optimization (PPO) and outperforms existing novelty-seeking exploration methods including count-based exploration even in continuous control tasks, indicating that it improves the sample efficiency by preventing the agent from taking redundant actions. 1

For agents

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

get_harvested_code_for_paper("2107.06405")
get_code_for_paper("2107.06405")
have("2107.06405")

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

curl https://syntology.ai/api/ran/2107.06405.json

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

[![Syntology run record](https://syntology.ai/api/ran/2107.06405.svg)](https://syntology.ai/paper/2107.06405)

Connect an agent — have() is free.