Towards Multi-Agent Reinforcement Learning using Quantum Boltzmann Machines

09/22/2021
by   Tobias Müller, et al.
0

Reinforcement learning has driven impressive advances in machine learning. Simultaneously, quantum-enhanced machine learning algorithms using quantum annealing underlie heavy developments. Recently, a multi-agent reinforcement learning (MARL) architecture combining both paradigms has been proposed. This novel algorithm, which utilizes Quantum Boltzmann Machines (QBMs) for Q-value approximation has outperformed regular deep reinforcement learning in terms of time-steps needed to converge. However, this algorithm was restricted to single-agent and small 2x2 multi-agent grid domains. In this work, we propose an extension to the original concept in order to solve more challenging problems. Similar to classic DQNs, we add an experience replay buffer and use different networks for approximating the target and policy values. The experimental results show that learning becomes more stable and enables agents to find optimal policies in grid-domains with higher complexity. Additionally, we assess how parameter sharing influences the agents behavior in multi-agent domains. Quantum sampling proves to be a promising method for reinforcement learning tasks, but is currently limited by the QPU size and therefore by the size of the input and Boltzmann machine.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/17/2016

Reinforcement Learning Using Quantum Boltzmann Machines

We investigate whether quantum annealers with select chip layouts can ou...
research
05/29/2017

Free energy-based reinforcement learning using a quantum processor

Recent theoretical and experimental results suggest the possibility of u...
research
11/24/2022

Software Simulation and Visualization of Quantum Multi-Drone Reinforcement Learning

Quantum machine learning (QML) has received a lot of attention according...
research
04/19/2019

Teaching on a Budget in Multi-Agent Deep Reinforcement Learning

Deep Reinforcement Learning algorithms can solve complex sequential deci...
research
06/14/2020

Comparative Evaluation of Multi-Agent Deep Reinforcement Learning Algorithms

Multi-agent deep reinforcement learning (MARL) suffers from a lack of co...
research
08/22/2022

Quantum Multi-Agent Meta Reinforcement Learning

Although quantum supremacy is yet to come, there has recently been an in...
research
12/07/2021

QKSA: Quantum Knowledge Seeking Agent – resource-optimized reinforcement learning using quantum process tomography

In this research, we extend the universal reinforcement learning (URL) a...

Please sign up or login with your details

Forgot password? Click here to reset