Parametrized Quantum Policies for Reinforcement LearningDownload PDF

21 May 2021, 20:49 (edited 27 Oct 2021)NeurIPS 2021 PosterReaders: Everyone
  • Keywords: reinforcement learning, quantum computing, parametrized quantum circuits, quantum neural networks, policy gradient, quantum machine learning, quantum reinforcement learning, quantum, variational quantum circuits
  • TL;DR: We investigate the potential of parametrized quantum computations when trained as reinforcement learning policies in classical environments.
  • Abstract: With the advent of real-world quantum computing, the idea that parametrized quantum computations can be used as hypothesis families in a quantum-classical machine learning system is gaining increasing traction. Such hybrid systems have already shown the potential to tackle real-world tasks in supervised and generative learning, and recent works have established their provable advantages in special artificial tasks. Yet, in the case of reinforcement learning, which is arguably most challenging and where learning boosts would be extremely valuable, no proposal has been successful in solving even standard benchmarking tasks, nor in showing a theoretical learning advantage over classical algorithms. In this work, we achieve both. We propose a hybrid quantum-classical reinforcement learning model using very few qubits, which we show can be effectively trained to solve several standard benchmarking environments. Moreover, we demonstrate, and formally prove, the ability of parametrized quantum circuits to solve certain learning tasks that are intractable to classical models, including current state-of-art deep neural networks, under the widely-believed classical hardness of the discrete logarithm problem.
  • Supplementary Material: pdf
  • Code Of Conduct: I certify that all co-authors of this work have read and commit to adhering to the NeurIPS Statement on Ethics, Fairness, Inclusivity, and Code of Conduct.
  • Code: https://www.tensorflow.org/quantum/tutorials/quantum_reinforcement_learning
12 Replies

Loading