SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2404.05055 · NeurIPS · 2023

Percentile Criterion Optimization in Offline Reinforcement Learning

Marek Petrik, Cyrus Cousins, Elita Lobo, Yair Zick

arXiv · PDF · Open in the Atlas

Code that ran

6 of 9 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, 2 violated it and 0 have no contract verdict; 3 failures of our instrument; 3 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/2404.05055.json · badge: /api/ran/2404.05055.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
elitalobo/varframework canonical (classifier label)
classifier basis: census
6 ran · 3 no recorded run
FunctionStatusWhere it lives
compute_covariance Ran
ran, violated the contract we drafted
elitalobo/varframework/src/plot_radii.py
pointer only (licence: NONE) · get_code("f2b3e7b71b5c895c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, elitalobo/varframework 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.

load_nsa Ran
ran, honoured the contract we drafted
elitalobo/varframework/src/algorithms.py
pointer only (licence: NONE) · get_code("e123e2efd7912694")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, elitalobo/varframework 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.

permute_point Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
elitalobo/varframework/src/plot_ternary.py
pointer only (licence: NONE) · get_code("02051dc1bb24f648")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, elitalobo/varframework 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.

project_point Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
elitalobo/varframework/src/plot_ternary.py
pointer only (licence: NONE) · get_code("3a8ea5b39d16b89e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, elitalobo/varframework 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.

unzip Ran
ran; our contract draft was wrong, not the code
elitalobo/varframework/src/plot_ternary.py
pointer only (licence: NONE) · get_code("566b67b5fd055137")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, elitalobo/varframework 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.

validate_transitionp Ran
ran, violated the contract we drafted
elitalobo/varframework/src/algorithms.py
pointer only (licence: NONE) · get_code("79aeeca51b756813")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, elitalobo/varframework 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.

compute_dist Not yet run
unverified (harvested, no recorded run)
elitalobo/varframework/src/plot_radii.py
pointer only (licence: NONE) · get_code("4b7502512933d5f0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, elitalobo/varframework 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. No invocation recorded.

load_initial Not yet run
unverified (harvested, no recorded run)
elitalobo/varframework/src/algorithms.py
pointer only (licence: NONE) · get_code("b50ac088edfdc3dc")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, elitalobo/varframework 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. No invocation recorded.

validate_bcr Not yet run
unverified (harvested, no recorded run)
elitalobo/varframework/src/plot_radii.py
pointer only (licence: NONE) · get_code("a6f52c6798c3197c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, elitalobo/varframework 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. No invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 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 9 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 reinforcement learning, robust policies for high-stakes decision-making problems with limited data are usually computed by optimizing the percentile criterion. The percentile criterion is approximately solved by constructing an ambiguity set that contains the true model with high probability and optimizing the policy for the worst model in the set. Since the percentile criterion is non-convex, constructing ambiguity sets is often challenging. Existing work uses Bayesian credible regions as ambiguity sets, but they are often unnecessarily large and result in learning overly conservative policies. To overcome these shortcomings, we propose a novel Valueat-Risk based dynamic programming algorithm to optimize the percentile criterion without explicitly constructing any ambiguity sets. Our theoretical and empirical results show that our algorithm implicitly constructs much smaller ambiguity sets and learns less conservative robust policies.

For agents

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

get_harvested_code_for_paper("2404.05055")
get_code_for_paper("2404.05055")
have("2404.05055")

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

curl https://syntology.ai/api/ran/2404.05055.json

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

[![Syntology run record](https://syntology.ai/api/ran/2404.05055.svg)](https://syntology.ai/paper/2404.05055)

Connect an agent — have() is free.