Generating neural architectures from parameter spaces for multi-agent reinforcement learning

We explore a data-driven approach to generating neural network parameters to determine whether generative models can capture the underlying distribution of a collection of neural network checkpoints. We compile a dataset of checkpoints from neural networks trained within the multi-agent reinforcemen...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Pattern recognition letters Jg. 185; S. 272 - 278
Hauptverfasser: Artaud, Corentin, De-Silva, Varuna, Pina, Rafael, Shi, Xiyu
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier B.V 01.09.2024
Schlagworte:
Generative models
Multi-agent reinforcement learning
Neural networks
Parameter generation
Transformers
Multi-agent reinforcement learning
Transformers
Parameter generation
Generative models
Neural networks
ISSN:0167-8655
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:We explore a data-driven approach to generating neural network parameters to determine whether generative models can capture the underlying distribution of a collection of neural network checkpoints. We compile a dataset of checkpoints from neural networks trained within the multi-agent reinforcement learning framework, thus potentially producing previously unseen combinations of neural network parameters. In particular, our generative model is a conditional transformer-based variational autoencoder that, when provided with random noise and a specified performance metric – in our context, returns – predicts the appropriate distribution over the parameter space to achieve the desired performance metric. Our method successfully generates parameters for a specified optimal return without further fine-tuning. We also show that the parameters generated using this approach are more constrained and less variable and, most importantly, perform on par with those trained directly under the multi-agent reinforcement learning framework. We test our method on the neural network architectures commonly employed in the most advanced state-of-the-art algorithms. •Variational autoencoders with multi-head self-attention architecture.•Generate dataset of neural networks and augmentation processes.•Generating from random noise neural network parameter conditioned on return.•Discuss implications in the context of MARL and perform analysis of generations vs traditional.
ISSN:0167-8655
DOI:10.1016/j.patrec.2024.07.013