Multi-Agent Quantum Reinforcement Learning using Evolutionary Optimization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kölle, Michael, Topp, Felix, Phan, Thomy, Altmann, Philipp, Nüßlein, Jonas, Linnhoff-Popien, Claudia
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913633230913536
author Kölle, Michael
Topp, Felix
Phan, Thomy
Altmann, Philipp
Nüßlein, Jonas
Linnhoff-Popien, Claudia
author_facet Kölle, Michael
Topp, Felix
Phan, Thomy
Altmann, Philipp
Nüßlein, Jonas
Linnhoff-Popien, Claudia
contents Multi-Agent Reinforcement Learning is becoming increasingly more important in times of autonomous driving and other smart industrial applications. Simultaneously a promising new approach to Reinforcement Learning arises using the inherent properties of quantum mechanics, reducing the trainable parameters of a model significantly. However, gradient-based Multi-Agent Quantum Reinforcement Learning methods often have to struggle with barren plateaus, holding them back from matching the performance of classical approaches. While gradient free Quantum Reinforcement Learning methods may alleviate some of these challenges, they too are not immune to the difficulties posed by barren plateaus. We build upon an existing approach for gradient free Quantum Reinforcement Learning and propose three genetic variations with Variational Quantum Circuits for Multi-Agent Reinforcement Learning using evolutionary optimization. We evaluate our genetic variations in the Coin Game environment and also compare them to classical approaches. We showed that our Variational Quantum Circuit approaches perform significantly better compared to a neural network with a similar amount of trainable parameters. Compared to the larger neural network, our approaches archive similar results using $97.88\%$ less parameters.
format Preprint
id arxiv_https___arxiv_org_abs_2311_05546
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Multi-Agent Quantum Reinforcement Learning using Evolutionary Optimization
Kölle, Michael
Topp, Felix
Phan, Thomy
Altmann, Philipp
Nüßlein, Jonas
Linnhoff-Popien, Claudia
Quantum Physics
Artificial Intelligence
Multiagent Systems
Multi-Agent Reinforcement Learning is becoming increasingly more important in times of autonomous driving and other smart industrial applications. Simultaneously a promising new approach to Reinforcement Learning arises using the inherent properties of quantum mechanics, reducing the trainable parameters of a model significantly. However, gradient-based Multi-Agent Quantum Reinforcement Learning methods often have to struggle with barren plateaus, holding them back from matching the performance of classical approaches. While gradient free Quantum Reinforcement Learning methods may alleviate some of these challenges, they too are not immune to the difficulties posed by barren plateaus. We build upon an existing approach for gradient free Quantum Reinforcement Learning and propose three genetic variations with Variational Quantum Circuits for Multi-Agent Reinforcement Learning using evolutionary optimization. We evaluate our genetic variations in the Coin Game environment and also compare them to classical approaches. We showed that our Variational Quantum Circuit approaches perform significantly better compared to a neural network with a similar amount of trainable parameters. Compared to the larger neural network, our approaches archive similar results using $97.88\%$ less parameters.
title Multi-Agent Quantum Reinforcement Learning using Evolutionary Optimization
topic Quantum Physics
Artificial Intelligence
Multiagent Systems
url https://arxiv.org/abs/2311.05546