AGENTFORGE: A Flexible Low-Code Platform for Reinforcement Learning Agent Design

Francisco E. Fernandes Jr., Antti Oulasvirta

2025

Abstract

Developing a reinforcement learning (RL) agent often involves identifying values for numerous parameters, covering the policy, reward function, environment, and agent-internal architecture. Since these parameters are interrelated in complex ways, optimizing them is a black-box problem that proves especially challenging for nonexperts. Although existing optimization-as-a-service platforms (e.g., Vizier and Optuna) can handle such problems, they are impractical for RL systems, since the need for manual user mapping of each parameter to distinct components makes the effort cumbersome. It also requires understanding of the optimization process, limiting the systems’ application beyond the machine learning field and restricting access in areas such as cognitive science, which models human decision-making. To tackle these challenges, the paper presents AGENTFORGE, a flexible low-code platform to optimize any parameter set across an RL system. Available at https://github.com/feferna/AgentForge, it allows an optimization problem to be defined in a few lines of code and handed to any of the interfaced optimizers. With AGENTFORGE, the user can optimize the parameters either individually or jointly. The paper presents an evaluation of its performance for a challenging vision-based RL problem.

Paper Citation

in Harvard Style

Fernandes Jr. F. and Oulasvirta A. (2025). AGENTFORGE: A Flexible Low-Code Platform for Reinforcement Learning Agent Design. In Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART; ISBN 978-989-758-737-5, SciTePress, pages 351-358. DOI: 10.5220/0013142900003890

in Bibtex Style

@conference{icaart25,
author={Francisco Fernandes Jr. and Antti Oulasvirta},
title={AGENTFORGE: A Flexible Low-Code Platform for Reinforcement Learning Agent Design},
booktitle={Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART},
year={2025},
pages={351-358},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013142900003890},
isbn={978-989-758-737-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART
TI - AGENTFORGE: A Flexible Low-Code Platform for Reinforcement Learning Agent Design
SN - 978-989-758-737-5
AU - Fernandes Jr. F.
AU - Oulasvirta A.
PY - 2025
SP - 351
EP - 358
DO - 10.5220/0013142900003890
PB - SciTePress