Policy gradients using variational quantum circuits
Open Access
- 11 April 2023
- journal article
- research article
- Published by Springer Nature in Quantum Machine Intelligence
- Vol. 5 (1) , 1-15
Abstract
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 ????-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.Keywords
All Related Versions
This publication has 42 references indexed in Scilit:
- Machine learning & artificial intelligence in the quantum domain: a review of recent progressReports on Progress in Physics, 2018
- A Tutorial on Fisher informationJournal of Mathematical Psychology, 2017
- Advances in quantum reinforcement learning2017
- Quantum-Enhanced Machine LearningPhysical Review Letters, 2016
- Mastering the game of Go with deep neural networks and tree searchNature, 2016
- Quantum Speedup for Active Learning AgentsPhysical Review X, 2014
- Machine Learning in a Quantum World2006
- FAULT-TOLERANT QUANTUM COMPUTATION1998
- Simple statistical gradient-following algorithms for connectionist reinforcement learningMachine Learning, 1992
- Probability Inequalities for Sums of Bounded Random VariablesJournal of the American Statistical Association, 1963