Quantum reinforcement learning Comparing quantum annealing and gate-based quantum computing with classical deep reinforcement learning

In this paper, we present implementations of an annealing-based and a gate-based quantum computing approach for finding the optimal policy to traverse a grid and compare them to a classical deep reinforcement learning approach. We extended these three approaches by allowing for stochastic actions instead of deterministic actions and by introducing a new learning technique called curriculum learning. With curriculum learning, we gradually increase the complexity of the environment and we find that it has a positive effect on the expected reward of a traversal. We see that the number of training steps needed for the two quantum approaches is lower than that needed for the classical approach.

Automated summary

In this paper, two quantum computing approaches, annealing-based and gate-based, are implemented and compared to a classical deep reinforcement learning approach for finding the optimal policy in a grid traversal task. Stochastic actions and curriculum learning are introduced to enhance the three approaches. The results show that curriculum learning improves the expected reward of traversal and the quantum approaches require fewer training steps compared to the classical approach.