Multi-agent reinforcement learning using simulated quantum annealing

Multi-agent reinforcement learning using simulated quantum annealing

Neumann, N.M.P.
de Heer, P.B.U.L.
Chiscop, I.
Phillipson, F.

2020

With quantum computers still under heavy development, already numerous quantum machine learning algorithms have been proposed for both gate-based quantum computers and quantum annealers. Recently, a quantum annealing version of a reinforcement learning algorithm for grid-traversal using one agent was published. We extend this work based on quantum Boltzmann machines, by allowing for any number of agents. We show that the use of quantum annealing can improve the learning compared to classical methods. We do this both by means of actual quantum hardware and by simulated quantum annealing.

Multi-agent
Reinforced learning
Quantum computing
D-Wave
Quantum annealing

http://resolver.tudelft.nl/uuid:499be90f-d120-4373-802c-02db94df99e6

875788

International Conference on Computational Science (ICCS)

plaats en datum ontbreken: conferentie afgelast. proceedings worden later gepubliceerd

conference paper