Quantum Reinforcement Learning for Solving a Stochastic Frozen Lake Environment and the Impact of Architecture and Optimizer Choices

Under CopyrightDragan, Theodora-AugustinaTheodora-AugustinaDraganMonnet, MaureenMaureenMonnetMendl, Christian B.Christian B.MendlLorenz, Jeanette MiriamJeanette MiriamLorenz2023-10-052023-10-052023https://publica.fraunhofer.de/handle/publica/451330https://doi.org/10.24406/publica-193910.24406/publica-1939enquantum reinforcement learningproximal policy optimizationfrozen lakeexpressibilityentanglement capabilityeffective dimensionparametrised quantum circuitsquantum metricsencodingQuantum Reinforcement Learning for Solving a Stochastic Frozen Lake Environment and the Impact of Architecture and Optimizer Choicespresentation