Bandit approach to conflict-free multi-agent Q-learning in view of photonic implementation

Recently, extensive studies on photonic reinforcement learning to accelerate the process of calculation by exploiting the physical nature of light have been conducted. Previous studies utilized quantum interference of photons to achieve collective decision-making without choice conflicts when solvin...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2022-12
Main Authors: Shinkawa, Hiroaki, Chauvet, Nicolas, Röhm, André, Takatomo Mihana, Horisaki, Ryoichi, Bachelier, Guillaume, Naruse, Makoto
Format: Article
Language:English
Subjects:
Algorithms
Decision making
Gaming machines
Interference
Machine learning
Multiagent systems
Photonics
Reagents
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Recently, extensive studies on photonic reinforcement learning to accelerate the process of calculation by exploiting the physical nature of light have been conducted. Previous studies utilized quantum interference of photons to achieve collective decision-making without choice conflicts when solving the competitive multi-armed bandit problem, a fundamental example of reinforcement learning. However, the bandit problem deals with a static environment where the agent's action does not influence the reward probabilities. This study aims to extend the conventional approach to a more general multi-agent reinforcement learning targeting the grid world problem. Unlike the conventional approach, the proposed scheme deals with a dynamic environment where the reward changes because of agents' actions. A successful photonic reinforcement learning scheme requires both a photonic system that contributes to the quality of learning and a suitable algorithm. This study proposes a novel learning algorithm, discontinuous bandit Q-learning, in view of a potential photonic implementation. Here, state-action pairs in the environment are regarded as slot machines in the context of the bandit problem and an updated amount of Q-value is regarded as the reward of the bandit problem. We perform numerical simulations to validate the effectiveness of the bandit algorithm. In addition, we propose a multi-agent architecture in which agents are indirectly connected through quantum interference of light and quantum principles ensure the conflict-free property of state-action pair selections among agents. We demonstrate that multi-agent reinforcement learning can be accelerated owing to conflict avoidance among multiple agents.
ISSN:2331-8422