Quantum Binary Neural Networks for Reinforcement Learning
Andrew Haverly, Shahram Rahimi, M. A. Novotny · 2025
This paper presents an adaptation of the quantum binary neural network (QBNN) to reinforcement learning, enabling the network to efficiently train on a classically intractable number of agent-environment-state-action-reward combinations. We demonstrate the feasibility of this approach through its application to the gridworld task, showcasing the potential of QBNNs in handling complex, high-dimensional reinforcement learning problems. This work provides a foundation for further exploration of QBNNs in more complex reinforcement learning environments.