MADQRL: Distributed Quantum Reinforcement Learning Framework for Multi-Agent Environments

TL;DR

MADQRL introduces a distributed quantum reinforcement learning framework for multi-agent systems, improving efficiency and performance in high-dimensional environments by leveraging quantum computing principles.

Contribution

It proposes a novel distributed quantum RL framework that enables multiple agents to learn independently, reducing computational load and enhancing performance in complex multi-agent environments.

Findings

Achieved approximately 10% improvement over other distribution strategies.

Achieved approximately 5% improvement over classical policy models.

Validated on cooperative-pong environment with positive results.

Abstract

Reinforcement learning (RL) is one of the most practical ways to learn from real-life use-cases. Motivated from the cognitive methods used by humans makes it a widely acceptable strategy in the field of artificial intelligence. Most of the environments used for RL are often high-dimensional, and traditional RL algorithms becomes computationally expensive and challenging to effectively learn from such systems. Recent advancements in practical demonstration of quantum computing (QC) theories, such as compact encoding, enhanced representation and learning algorithms, random sampling, or the inherent stochastic nature of quantum systems, have opened up new directions to tackle these challenges. Quantum reinforcement learning (QRL) is seeking significant traction over the past few years. However, the current state of quantum hardware is not enough to cater for such high-dimensional environments with complex multi-agent setup. To tackle this issue, we propose a distributed framework for QRL where multiple agents learn independently, distributing the load of joint training from individual machines. Our method works well for environments with disjoint sets of action and observation spaces, but can also be extended to other systems with reasonable approximations. We analyze the proposed method on cooperative-pong environment and our results indicate ~10% improvement from other distribution strategies, and ~5% improvement from classical models of policy representation.