Variational quantum reinforcement learning via evolutionary optimization
Abstract
Recent advances in classical reinforcement learning (RL) and quantum computation point to a promising direction for performing RL on a quantum computer. However, potential applications in quantum RL are limited by the number of qubits available in modern quantum devices. Here, we present two frameworks for deep quantum RL tasks using gradient-free evolutionary optimization. First, we apply the amplitude encoding scheme to the Cart-Pole problem, where we demonstrate the quantum advantage of parameter saving using amplitude encoding. Second, we propose a hybrid framework where the quantum RL agents are equipped with a hybrid tensor network-variational quantum circuit (TN-VQC) architecture to handle inputs of dimensions exceeding the number of qubits. This allows us to perform quantum RL in the MiniGrid environment with 147-dimensional inputs. The hybrid TN-VQC architecture provides a natural way to perform efficient compression of the input dimension, enabling further quantum RL applications on noisy intermediate-scale quantum devices.
Document Details
- Document Type
- Pub Defense Publication
- Publication Date
- Feb 15, 2022
- Source ID
- 10.1088/2632-2153/ac4559
Entities
People
- Chia-wei Hsing
- Chih-min Huang
- Hsi-Sheng Goan
- Samuel Yen-Chi Chen
- Ying-Jer Kao
Organizations
- Brookhaven National Laboratory
- Ministry of Science and Technology, Israel
- National Taiwan University
- United States Air Force