Scilab-RL: A software framework for efficient reinforcement learning and cognitive modeling research
One problem with researching cognitive modeling and reinforcement learning (RL) is that researchers spend too much time on setting up an appropriate computational framework for their experiments. Many open source implementations of current RL algorithms exist, but there is a lack of a modular suite...
Saved in:
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2025-02-01
|
Series: | SoftwareX |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2352711025000317 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
_version_ | 1832573161593372672 |
---|---|
author | Jan Benad Frank Röder Manfred Eppe |
author_facet | Jan Benad Frank Röder Manfred Eppe |
author_sort | Jan Benad |
collection | DOAJ |
description | One problem with researching cognitive modeling and reinforcement learning (RL) is that researchers spend too much time on setting up an appropriate computational framework for their experiments. Many open source implementations of current RL algorithms exist, but there is a lack of a modular suite of tools combining different robotic simulators and platforms, data visualization, hyperparameter optimization, and baseline experiments. To address this problem, we present Scilab-RL, a software framework for efficient research in cognitive modeling and reinforcement learning for robotic agents. The framework focuses on goal-conditioned reinforcement learning using Stable Baselines 3, CleanRL and the Gymnasium interface. It enables native possibilities for experiment visualizations and hyperparameter optimization. We describe how these features enable researchers to conduct experiments with minimal time effort, thus maximizing research output. |
format | Article |
id | doaj-art-949c38962575427c80aa995d0ed3033e |
institution | Kabale University |
issn | 2352-7110 |
language | English |
publishDate | 2025-02-01 |
publisher | Elsevier |
record_format | Article |
series | SoftwareX |
spelling | doaj-art-949c38962575427c80aa995d0ed3033e2025-02-02T05:27:43ZengElsevierSoftwareX2352-71102025-02-0129102064Scilab-RL: A software framework for efficient reinforcement learning and cognitive modeling researchJan Benad0Frank Röder1Manfred Eppe2Corresponding author.; Institute for Data Science Foundations, Hamburg University of Technology, Hamburg, GermanyInstitute for Data Science Foundations, Hamburg University of Technology, Hamburg, GermanyInstitute for Data Science Foundations, Hamburg University of Technology, Hamburg, GermanyOne problem with researching cognitive modeling and reinforcement learning (RL) is that researchers spend too much time on setting up an appropriate computational framework for their experiments. Many open source implementations of current RL algorithms exist, but there is a lack of a modular suite of tools combining different robotic simulators and platforms, data visualization, hyperparameter optimization, and baseline experiments. To address this problem, we present Scilab-RL, a software framework for efficient research in cognitive modeling and reinforcement learning for robotic agents. The framework focuses on goal-conditioned reinforcement learning using Stable Baselines 3, CleanRL and the Gymnasium interface. It enables native possibilities for experiment visualizations and hyperparameter optimization. We describe how these features enable researchers to conduct experiments with minimal time effort, thus maximizing research output.http://www.sciencedirect.com/science/article/pii/S2352711025000317Reinforcement learningCognitive modelingRoboticsPython |
spellingShingle | Jan Benad Frank Röder Manfred Eppe Scilab-RL: A software framework for efficient reinforcement learning and cognitive modeling research SoftwareX Reinforcement learning Cognitive modeling Robotics Python |
title | Scilab-RL: A software framework for efficient reinforcement learning and cognitive modeling research |
title_full | Scilab-RL: A software framework for efficient reinforcement learning and cognitive modeling research |
title_fullStr | Scilab-RL: A software framework for efficient reinforcement learning and cognitive modeling research |
title_full_unstemmed | Scilab-RL: A software framework for efficient reinforcement learning and cognitive modeling research |
title_short | Scilab-RL: A software framework for efficient reinforcement learning and cognitive modeling research |
title_sort | scilab rl a software framework for efficient reinforcement learning and cognitive modeling research |
topic | Reinforcement learning Cognitive modeling Robotics Python |
url | http://www.sciencedirect.com/science/article/pii/S2352711025000317 |
work_keys_str_mv | AT janbenad scilabrlasoftwareframeworkforefficientreinforcementlearningandcognitivemodelingresearch AT frankroder scilabrlasoftwareframeworkforefficientreinforcementlearningandcognitivemodelingresearch AT manfredeppe scilabrlasoftwareframeworkforefficientreinforcementlearningandcognitivemodelingresearch |