SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2111.06920 · NeurIPS · 2021

Neural optimal feedback control with local learning rules

Siavash Golkar, Anirvan Sengupta, Dmitri Chklovskii, Johannes Friedrich, Shiva Farashahi, Alexander Genkin

arXiv · PDF · Open in the Atlas

Code that ran

1 of 5 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; 4 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/2111.06920.json · badge: /api/ran/2111.06920.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
j-friedrich/neuralofc canonical (classifier label)
classifier basis: classifier_2025
1 ran · 3 no recorded run
golkar/bio-ofc-gym canonical (classifier label)
classifier basis: classifier_2025
0 ran · 1 no recorded run
FunctionStatusWhere it lives
parmap Ran
ran on a synthesized input
j-friedrich/neuralofc/ofc.py
code served (permissive licence) · get_code("1b6ad5783288ff6f")
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 2, dtype family int; 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 multiprocessing
import numpy as np

# Define a simple function that will be mapped over the data
def simple_function(x):
    """A simple function that squares the input"""
    return x ** 2

# Create test data - a list of small arrays
X = [np.array([1, 2, 3]), np.array([4, 5, 6]), np.array([7, 8, 9])]

# Define the arguments dictionary
ARGS = {
    'f': simple_function,
    'X': X,
    'nprocs': 2
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 2, 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
Riccati Not yet run
unverified (harvested, no recorded run)
j-friedrich/neuralofc/ofc.py
code served (permissive licence) · get_code("115cd180fb704c55")
How it ran

no invocation recorded.

Riccati Not yet run
unverified (harvested, no recorded run)
j-friedrich/neuralofc/ofc.py
code served (permissive licence) · get_code("e46a8452f2a7da7f")
How it ran

no invocation recorded.

System Not yet run
unverified (harvested, no recorded run)
j-friedrich/neuralofc/ofc.py
code served (permissive licence) · get_code("7c4de2ef8e6d23c6")
How it ran

no invocation recorded.

bio_ofc_train Not yet run
unverified (harvested, no recorded run)
golkar/bio-ofc-gym/bio_ofc.py
pointer only (licence: NONE) · get_code("342326966d83720d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, golkar/bio-ofc-gym 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 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 4 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 4 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

A major problem in motor control is understanding how the brain plans and executes proper movements in the face of delayed and noisy stimuli. A prominent framework for addressing such control problems is Optimal Feedback Control (OFC). OFC generates control actions that optimize behaviorally relevant criteria by integrating noisy sensory stimuli and the predictions of an internal model using the Kalman filter or its extensions. However, a satisfactory neural model of Kalman filtering and control is lacking because existing proposals have the following limitations: not considering the delay of sensory feedback, training in alternating phases, and requiring knowledge of the noise covariance matrices, as well as that of systems dynamics. Moreover, the majority of these studies considered Kalman filtering in isolation, and not jointly with control. To address these shortcomings, we introduce a novel online algorithm which combines adaptive Kalman filtering with a model free control approach (i.e., policy gradient algorithm). We implement this algorithm in a biologically plausible neural network with local synaptic plasticity rules. This network performs system identification and Kalman filtering, without the need for multiple phases with distinct update rules or the knowledge of the noise covariances. It can perform state estimation with delayed sensory feedback, with the help of an internal model. It learns the control policy without requiring any knowledge of the dynamics, thus avoiding the need for weight transport. In this way, our implementation of OFC solves the credit assignment problem needed to produce the appropriate sensory-motor control in the presence of stimulus delay.

For agents

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

get_harvested_code_for_paper("2111.06920")
get_code_for_paper("2111.06920")
have("2111.06920")

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

curl https://syntology.ai/api/ran/2111.06920.json

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

[![Syntology run record](https://syntology.ai/api/ran/2111.06920.svg)](https://syntology.ai/paper/2111.06920)

Connect an agent — have() is free.