SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1905.09191 · 2019

Learning Robust Options by Conditional Value at Risk Optimization

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; 1 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 0 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/1905.09191.json · badge: /api/ran/1905.09191.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
TakuyaHiraoka/Learning-Robust-Options-by-Conditional-Value-at-Risk-Optimization canonical (classifier label)
classifier basis: census
3 ran · 1 no recorded run
FunctionStatusWhere it lives
find_all_key_files_path Ran
ran on a synthesized input
TakuyaHiraoka/Learning-Robust-Options-by-Conditional-Value-at-Risk-Optimization/Scores4EachParameterPerturbation.py
code served (permissive licence) · get_code("9ba2f70546cf0616")
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 os
import re
import tempfile
import shutil

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

# Create some nested directories and files
os.makedirs(os.path.join(temp_dir, "subdir1"), exist_ok=True)
os.makedirs(os.path.join(temp_dir, "subdir2"), exist_ok=True)

# Create test files matching the pattern
open(os.path.join(temp_dir, "keyfile_test.txt"), "w").close()
open(os.path.join(temp_dir, "subdir1", "my_keyfile_data.txt"), "w").close()
open(os.path.join(temp_dir, "subdir1", "other_file.dat"), "w").close()
open(os.path.join(temp_dir, "subdir2", "keyfile.txt"), "w").close()
open(os.path.join(temp_dir, "subdir2", "not_matching.txt"), "w").close()

ARGS = {
    "directory": temp_dir,
    "keyfile_name": "keyfile"
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — 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
find_all_key_files_path Ran
ran on a synthesized input
TakuyaHiraoka/Learning-Robust-Options-by-Conditional-Value-at-Risk-Optimization/EvalAverageCVaR.py
code served (permissive licence) · get_code("139b7d9b5bb0e203")
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 os
import re
import tempfile
import shutil

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

# Create some nested directories and files
os.makedirs(os.path.join(temp_dir, "subdir1"), exist_ok=True)
os.makedirs(os.path.join(temp_dir, "subdir2", "nested"), exist_ok=True)

# Create files matching the key pattern
open(os.path.join(temp_dir, "keyfile.txt"), "w").close()
open(os.path.join(temp_dir, "subdir1", "my_keyfile_data.txt"), "w").close()
open(os.path.join(temp_dir, "subdir2", "nested", "keyfile_backup.pem"), "w").close()
open(os.path.join(temp_dir, "subdir2", "other_file.txt"), "w").close()

# Create files that don't match
open(os.path.join(temp_dir, "readme.md"), "w").close()
open(os.path.join(temp_dir, "subdir1", "document.pdf"), "w").close()

ARGS = {
    "directory": temp_dir,
    "keyfile_name": "keyfile"
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — 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
flatten_lists Ran
ran, honoured the contract we drafted
TakuyaHiraoka/Learning-Robust-Options-by-Conditional-Value-at-Risk-Optimization/LearningMoreRobustOption/pposgd_simple.py
pointer only (licence: MIT); the stored copy get_code serves, from Jekyll1021/RARL, is pointer only (licence: NONE) · get_code("0173e4280d9a9884")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from Jekyll1021/RARL, and GitHub detected no licence in that repository 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.

dense3D2 Not yet run
unverified (harvested, no recorded run)
TakuyaHiraoka/Learning-Robust-Options-by-Conditional-Value-at-Risk-Optimization/LearningMoreRobustOption/mlp_policy.py
code served (permissive licence) · get_code("c87dbab117f0acc8")
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, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 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.

FunctionAlso present inEarliest-datedOthers named
flatten_lists 8 other papers
3 dated earlier, 5 later
1606.03476 (2016-06)
Generative Adversarial Imitation Learning
1703.02702 (2017-03)
Robust Adversarial Reinforcement Learning
1801.01432 (2018-01)
Jointly Learning to Construct and Control Agents using Deep Reinforcement Learning
and 5 more not named here

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

Options are generally learned by using an inaccurate environment model (or simulator), which contains uncertain model parameters. While there are several methods to learn options that are robust against the uncertainty of model parameters, these methods only consider either the worst case or the average (ordinary) case for learning options. This limited consideration of the cases often produces options that do not work well in the unconsidered case. In this paper, we propose a conditional value at risk (CVaR)-based method to learn options that work well in both the average and worst cases. We extend the CVaR-based policy gradient method proposed by Chow and Ghavamzadeh (2014) to deal with robust Markov decision processes and then apply the extended method to learning robust options. We conduct experiments to evaluate our method in multi-joint robot control tasks (HopperIceBlock, Half-Cheetah, and Walker2D). Experimental results show that our method produces options that 1) give better worst-case performance than the options learned only to minimize the average-case loss, and 2) give better average-case performance than the options learned only to minimize the worst-case loss.

For agents

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

get_harvested_code_for_paper("1905.09191")
get_code_for_paper("1905.09191")
have("1905.09191")

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

curl https://syntology.ai/api/ran/1905.09191.json

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

[![Syntology run record](https://syntology.ai/api/ran/1905.09191.svg)](https://syntology.ai/paper/1905.09191)

Connect an agent — have() is free.