Utilize este identificador para referenciar este registo:
https://hdl.handle.net/1822/90180
Título: | Policy gradients using variational quantum circuits |
Autor(es): | Sequeira, André Santos, Luís Paulo Barbosa, L. S. |
Palavras-chave: | Quantum machine learning Reinforcement learning Policy gradients Quantum control |
Data: | Abr-2023 |
Editora: | Springer |
Revista: | Quantum Machine Intelligence |
Citação: | Sequeira, A., Santos, L.P. & Barbosa, L.S. Policy gradients using variational quantum circuits. Quantum Mach. Intell. 5, 18 (2023). https://doi.org/10.1007/s42484-023-00101-8 |
Resumo(s): | Variational quantum circuits are being used as versatile quantum machine learning models. Some empirical results exhibit an advantage in supervised and generative learning tasks. However, when applied to reinforcement learning, less is known. In this work, we considered a variational quantum circuit composed of a low-depth hardware-efficient ansatz as the parameterized policy of a reinforcement learning agent. We show that an epsilon-approximation of the policy gradient can be obtained using a logarithmic number of samples concerning the total number of parameters. We empirically verify that such quantum models behave similarly to typical classical neural networks used in standard benchmarking environments and quantum control, using only a fraction of the parameters. Moreover, we study the barren plateau phenomenon in quantum policy gradients using the Fisher information matrix spectrum. |
Tipo: | Artigo |
URI: | https://hdl.handle.net/1822/90180 |
DOI: | 10.1007/s42484-023-00101-8 |
ISSN: | 2524-4906 |
e-ISSN: | 2524-4914 |
Versão da editora: | https://link.springer.com/article/10.1007/s42484-023-00101-8#citeas |
Arbitragem científica: | yes |
Acesso: | Acesso aberto |
Aparece nas coleções: | HASLab - Artigos em revistas internacionais |
Ficheiros deste registo:
Ficheiro | Descrição | Tamanho | Formato | |
---|---|---|---|---|
2023-QuantumMachineIntelligence.pdf | 2,37 MB | Adobe PDF | Ver/Abrir |