Saved in:
Bibliographic Details
Main Authors: Kooi, Jacob E., Yang, Zhao, François-Lavet, Vincent
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.15345
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912389162598400
author Kooi, Jacob E.
Yang, Zhao
François-Lavet, Vincent
author_facet Kooi, Jacob E.
Yang, Zhao
François-Lavet, Vincent
contents Neural network architectures have a large impact in machine learning. In reinforcement learning, network architectures have remained notably simple, as changes often lead to small gains in performance. This work introduces a novel encoder architecture for pixel-based model-free reinforcement learning. The Hadamax (\textbf{Hada}mard \textbf{max}-pooling) encoder achieves state-of-the-art performance by max-pooling Hadamard products between GELU-activated parallel hidden layers. Based on the recent PQN algorithm, the Hadamax encoder achieves state-of-the-art model-free performance in the Atari-57 benchmark. Specifically, without applying any algorithmic hyperparameter modifications, Hadamax-PQN achieves an 80\% performance gain over vanilla PQN and significantly surpasses Rainbow-DQN. For reproducibility, the full code is available on \href{https://github.com/Jacobkooi/Hadamax}{GitHub}.
format Preprint
id arxiv_https___arxiv_org_abs_2505_15345
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Hadamax Encoding: Elevating Performance in Model-Free Atari
Kooi, Jacob E.
Yang, Zhao
François-Lavet, Vincent
Machine Learning
Artificial Intelligence
Neural network architectures have a large impact in machine learning. In reinforcement learning, network architectures have remained notably simple, as changes often lead to small gains in performance. This work introduces a novel encoder architecture for pixel-based model-free reinforcement learning. The Hadamax (\textbf{Hada}mard \textbf{max}-pooling) encoder achieves state-of-the-art performance by max-pooling Hadamard products between GELU-activated parallel hidden layers. Based on the recent PQN algorithm, the Hadamax encoder achieves state-of-the-art model-free performance in the Atari-57 benchmark. Specifically, without applying any algorithmic hyperparameter modifications, Hadamax-PQN achieves an 80\% performance gain over vanilla PQN and significantly surpasses Rainbow-DQN. For reproducibility, the full code is available on \href{https://github.com/Jacobkooi/Hadamax}{GitHub}.
title Hadamax Encoding: Elevating Performance in Model-Free Atari
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2505.15345