SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2409.04792 · NeurIPS · 2024

Improving Deep Reinforcement Learning by Reducing the Chain Effect of Value and Policy Churn

Hongyao Tang, Glen Berseth

arXiv · PDF · Open in the Atlas

Code that ran

4 of 4 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (3 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 0 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/2409.04792.json · badge: /api/ran/2409.04792.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
bluecontra/chain canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
bluecontra/CHAIN marked official in Papers with Code
Papers with Code archive
3 ran · 0 no recorded run
FunctionStatusWhere it lives
DoubleDQN_CHAIN Ran
ran on a synthesized input · constructed an object; no result was computed
bluecontra/CHAIN/minatar/agents/double_dqn_chain.py
pointer only (licence: NONE) · get_code("6f2dd65ce04506ad")
How it ran

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

QNetwork Ran
ran on a synthesized input · constructed an object; no result was computed
bluecontra/CHAIN/minatar/agents/double_dqn_chain.py
pointer only (licence: NONE) · get_code("2bc9d20a97ad4b7c")
How it ran

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

evaluate_policy Ran
ran, honoured the contract we drafted
bluecontra/chain/minatar/run_double_dqn_chain.py
pointer only (licence: NONE) · get_code("519bcb97d620e3bb")
How it ran

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

replay_buffer Ran
ran on a synthesized input · constructed an object; no result was computed
bluecontra/CHAIN/minatar/agents/double_dqn_chain.py
pointer only (licence: NONE) · get_code("878357e874462801")
How it ran

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

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 (0 with at least one paper dated earlier, 0 the same month, 2 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
QNetwork
brick of this paper's assembly: model
1 other paper
1 later · 1 only as an assembly brick
2506.00592 (2025-06)
Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn
replay_buffer
brick of this paper's assembly: helper
1 other paper
1 later · 1 only as an assembly brick
2506.00592 (2025-06)
Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn

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

Deep neural networks provide Reinforcement Learning (RL) powerful function approximators to address large-scale decision-making problems. However, these approximators introduce challenges due to the non-stationary nature of RL training. One source of the challenges in RL is that output predictions can churn, leading to uncontrolled changes after each batch update for states not included in the batch. Although such a churn phenomenon exists in each step of network training, how churn occurs and impacts RL remains under-explored. In this work, we start by characterizing churn in a view of Generalized Policy Iteration with function approximation, and we discover a chain effect of churn that leads to a cycle where the churns in value estimation and policy improvement compound and bias the learning dynamics throughout the iteration. Further, we concretize the study and focus on the learning issues caused by the chain effect in different settings, including greedy action deviation in value-based methods, trust region violation in proximal policy optimization, and dual bias of policy value in actor-critic methods. We then propose a method to reduce the chain effect across different settings, called Churn Approximated ReductIoN (CHAIN), which can be easily plugged into most existing DRL algorithms. Our experiments demonstrate the effectiveness of our method in both reducing churn and improving learning performance across online and offline, value-based and policy-based RL settings, as well as a scaling setting.

For agents

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

get_harvested_code_for_paper("2409.04792")
get_code_for_paper("2409.04792")
have("2409.04792")

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

curl https://syntology.ai/api/ran/2409.04792.json

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

[![Syntology run record](https://syntology.ai/api/ran/2409.04792.svg)](https://syntology.ai/paper/2409.04792)

Connect an agent — have() is free.