SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2401.09286 · 2024

Deployable Reinforcement Learning with Variable Control Rate

arXiv · PDF · Open in the Atlas

Code that ran

5 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; 3 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 2 failures of our instrument; 0 no recorded run), measured 2026-11-21; 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/2401.09286.json · badge: /api/ran/2401.09286.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
alpaficia/SEAC_Pytorch_release canonical (classifier label)
classifier basis: census
5 ran · 0 no recorded run
FunctionStatusWhere it lives
Action_adapter Ran
ran, honoured the contract we drafted
alpaficia/SEAC_Pytorch_release/Adapter.py
pointer only (licence: MIT); the stored copy get_code serves, from lqm00/a2p-sac, is pointer only (licence: NONE) · get_code("dbede9400bf58c5b")
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 lqm00/a2p-sac, 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.

Action_t_relu6_adapter Ran
ran, honoured the contract we drafted
alpaficia/SEAC_Pytorch_release/Adapter.py
code served (permissive licence) · get_code("4efe181a3a3fa4ec")
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 Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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 torch
import numpy as np

torch.manual_seed(0)

# Analyze the function:
# def Action_t_relu6_adapter(a, max_action):
#     return a / 6.0 * max_action
#
# Parameters:
# - a: a numeric value or tensor that can be divided by 6.0
# - max_action: a numeric value or tensor that can be multiplied
#
# The function performs element-wise division and multiplication,
# so both should be numeric types or tensors.

a = torch.randn(2, 4)
max_action = 2.0

ARGS = {
    "a": a,
    "max_action": max_action
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
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
Action_t_relu6_adapter_reverse Ran
ran, honoured the contract we drafted
alpaficia/SEAC_Pytorch_release/Adapter.py
code served (permissive licence) · get_code("7fde9410d5f59811")
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 Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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 torch

torch.manual_seed(0)

# The function takes two parameters:
# - act: appears to be a numeric value or tensor that gets multiplied
# - max_action: appears to be a numeric value or tensor used as divisor

# Create small tensor for act
act = torch.tensor([[1.0, 2.0, 3.0, 4.0], [5.0, 6.0, 7.0, 8.0]])

# Create scalar for max_action
max_action = 12.0

ARGS = {
    "act": act,
    "max_action": max_action
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
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
build_net Ran
ran; our contract draft was wrong, not the code
alpaficia/SEAC_Pytorch_release/SEAC.py
code served (permissive licence) · get_code("9b95be60df57db51")
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 Sequential. The image it ran in was not recorded. If your copy returns the same type 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 torch
import torch.nn as nn

torch.manual_seed(0)

# Analyze the function:
# - layer_shape: used with len() and indexing [j], [j+1] - needs to be a sequence of integers
# - activation: called with () to instantiate - needs to be a class (nn.Module)
# - output_activation: called with () to instantiate - needs to be a class (nn.Module)

ARGS = {
    "layer_shape": [4, 8, 6, 3],
    "activation": nn.ReLU,
    "output_activation": nn.Sigmoid,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 and dtype family float describe that coercion, not the output, and are not stated
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
coordinate_system_conversion Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
alpaficia/SEAC_Pytorch_release/envs/dynamic_world.py
code served (permissive licence) · get_code("c2c1aae2bf247d8d")
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 ndarray, ndim 1, dtype family float, shape (2,) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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 numpy as np

# The function takes a single parameter 'coordinate' which should be array-like
# Looking at the function body, it accesses coordinate[0] and coordinate[1]
# so it needs to be indexable with at least 2 elements

coordinate = np.array([0.5, -0.3])

ARGS = {
    "coordinate": coordinate
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family float, shape (2,) — shape (2,) as a later run recorded it
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

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 5 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 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
Action_adapter 2 other papers
1 dated earlier, 1 later
1812.05905 (2018-12)
Soft Actor-Critic Algorithms and Applications
2405.11982 (2024-05)
Robust Deep Reinforcement Learning with Adaptive Adversarial Perturbations in Action Space
build_net 1 other paper
1 dated earlier
1812.05905 (2018-12)
Soft Actor-Critic Algorithms and Applications

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 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Deploying controllers trained with Reinforcement Learning (RL) on real robots can be challenging: RL relies on agents' policies being modeled as Markov Decision Processes (MDPs), which assume an inherently discrete passage of time. The use of MDPs results in that nearly all RL-based control systems employ a fixed-rate control strategy with a period (or time step) typically chosen based on the developer's experience or specific characteristics of the application environment. Unfortunately, the system should be controlled at the highest, worst-case frequency to ensure stability, which can demand significant computational and energy resources and hinder the deployability of the controller on onboard hardware. Adhering to the principles of reactive programming, we surmise that applying control actions only when necessary enables the use of simpler hardware and helps reduce energy consumption. We challenge the fixed frequency assumption by proposing a variant of RL with variable control rate. In this approach, the policy decides the action the agent should take as well as the duration of the time step associated with that action. In our new setting, we expand Soft Actor-Critic (SAC) to compute the optimal policy with a variable control rate, introducing the Soft Elastic Actor-Critic (SEAC) algorithm. We show the efficacy of SEAC through a proof-of-concept simulation driving an agent with Newtonian kinematics. Our experiments show higher average returns, shorter task completion times, and reduced computational resources when compared to fixed rate policies.

For agents

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

get_harvested_code_for_paper("2401.09286")
get_code_for_paper("2401.09286")
have("2401.09286")

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

curl https://syntology.ai/api/ran/2401.09286.json

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

[![Syntology run record](https://syntology.ai/api/ran/2401.09286.svg)](https://syntology.ai/paper/2401.09286)

Connect an agent — have() is free.