2026-08-10T13:33:15Z https://drops.dagstuhl.de/oai

oai:drops-oai.dagstuhl.de:18323 2024-03-06T11:01:40Z ddc:004 open_access

Quantum Policy Gradient Algorithms Jerbi, Sofiene Cornelissen, Arjan Ozols, Maris Dunjko, Vedran quantum reinforcement learning policy gradient methods parametrized quantum circuits Understanding the power and limitations of quantum access to data in machine learning tasks is primordial to assess the potential of quantum computing in artificial intelligence. Previous works have already shown that speed-ups in learning are possible when given quantum access to reinforcement learning environments. Yet, the applicability of quantum algorithms in this setting remains very limited, notably in environments with large state and action spaces. In this work, we design quantum algorithms to train state-of-the-art reinforcement learning policies by exploiting quantum interactions with an environment. However, these algorithms only offer full quadratic speed-ups in sample complexity over their classical analogs when the trained policies satisfy some regularity conditions. Interestingly, we find that reinforcement learning policies derived from parametrized quantum circuits are well-behaved with respect to these conditions, which showcases the benefit of a fully-quantum reinforcement learning framework. Schloss Dagstuhl – Leibniz-Zentrum für Informatik Sofiene Jerbi and Arjan Cornelissen and Maris Ozols and Vedran Dunjko 2023 Is Part Of LIPIcs, Volume 266, 18th Conference on the Theory of Quantum Computation, Communication and Cryptography (TQC 2023) InProceedings Text doc-type:ResearchArticle publishedVersion application/pdf doi:10.4230/LIPIcs.TQC.2023.13 urn:nbn:de:0030-drops-183230 https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.TQC.2023.13 eng https://creativecommons.org/licenses/by/4.0/legalcode