SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2601.20765 · 2026

LESS IS MORE: CLUSTERED CROSS-COVARIANCE CON-TROL FOR OFFLINE RL

Sheng Yue, Ju Ren, Shuning Wang, Yongheng Deng, Nan Qiao

arXiv · PDF

Code that ran

1 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; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 0 failures of our instrument; 3 no recorded run), measured 2026-11-22; 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/2601.20765.json · badge: /api/ran/2601.20765.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
NanMuZ/C4 community
Papers with Code archive
1 ran · 3 no recorded run
FunctionStatusWhere it lives
GaussianNoise Ran
ran on a synthesized input
NanMuZ/C4/offlinerlkit/policy/model_free/c4cql.py
pointer only (licence: NONE) · get_code("447ccc87e5c42029")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, NanMuZ/C4 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.

BasePolicy Not yet run
unverified (harvested, no recorded run)
NanMuZ/C4/offlinerlkit/policy/model_free/c4cql.py
pointer only (licence: NONE) · get_code("f87ef2f5ecc1ce8e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, NanMuZ/C4 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.

C4CQLPolicy Not yet run
unverified (harvested, no recorded run)
NanMuZ/C4/offlinerlkit/policy/model_free/c4cql.py
pointer only (licence: NONE) · get_code("6ea3e19675d3f3b7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, NanMuZ/C4 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.

SACPolicy Not yet run
unverified (harvested, no recorded run)
NanMuZ/C4/offlinerlkit/policy/model_free/c4cql.py
pointer only (licence: NONE) · get_code("5445ab0c0a06b738")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, NanMuZ/C4 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 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, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 1 later) and 2 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
BasePolicy
brick of this paper's assembly: helper
9 other papers
8 dated earlier, 1 later · 6 only as an assembly brick
2005.13239 (2020-05)
MOPO: Model-based Offline Policy Optimization
2006.04779 (2020-06)
Conservative Q-Learning for Offline Reinforcement Learning
2102.08363 (2021-02)
COMBO: Conservative Offline Model-Based Policy Optimization
and 6 more not named here
SACPolicy
brick of this paper's assembly: helper
5 other papers
5 dated earlier · 3 only as an assembly brick
2005.13239 (2020-05)
MOPO: Model-based Offline Policy Optimization
2006.04779 (2020-06)
Conservative Q-Learning for Offline Reinforcement Learning
2102.08363 (2021-02)
COMBO: Conservative Offline Model-Based Policy Optimization
and 2 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

A fundamental challenge in offline reinforcement learning is distributional shift. Scarce data or datasets dominated by out-of-distribution (OOD) areas exacerbate this issue. Our theoretical analysis and experiments show that the standard squared error objective induces a harmful TD cross covariance. This effect amplifies in OOD areas, biasing optimization and degrading policy learning. To counteract this mechanism, we develop two complementary strategies: partitioned buffer sampling that restricts updates to localized replay partitions, attenuates irregular covariance effects, and aligns update directions, yielding a scheme that is easy to integrate with existing implementations, namely Clustered Cross-Covariance Control for TD (C 4 ). We also introduce an explicit gradient-based corrective penalty that cancels the covariance induced bias within each update. We prove that buffer partitioning preserves the lower bound property of the maximization objective, and that these constraints mitigate excessive conservatism in extreme OOD areas without altering the core behavior of policy constrained offline reinforcement learning. Empirically, our method showcases higher stability and up to 30% improvement in returns over prior methods, especially with small datasets and splits that emphasize OOD areas. The implementation code is available at https://github.com/NanMuZ/C4.

For agents

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

get_harvested_code_for_paper("2601.20765")
get_code_for_paper("2601.20765")
have("2601.20765")

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

curl https://syntology.ai/api/ran/2601.20765.json

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

[![Syntology run record](https://syntology.ai/api/ran/2601.20765.svg)](https://syntology.ai/paper/2601.20765)

Connect an agent — have() is free.