Quantum reinforcement learning

TL;DR

This paper introduces a novel quantum reinforcement learning framework that leverages quantum superposition and parallelism to enhance learning efficiency and balance exploration and exploitation in unknown probabilistic environments.

Contribution

It proposes a new QRL method combining quantum theory with reinforcement learning, including a value updating algorithm based on quantum principles, and analyzes its convergence and effectiveness.

Findings

QRL speeds up learning through quantum parallelism.

QRL effectively balances exploration and exploitation.

Simulated experiments demonstrate its superiority in complex problems.

Abstract

The key approaches for machine learning, especially learning in unknown probabilistic environments are new representations and computation mechanisms. In this paper, a novel quantum reinforcement learning (QRL) method is proposed by combining quantum theory and reinforcement learning (RL). Inspired by the state superposition principle and quantum parallelism, a framework of value updating algorithm is introduced. The state (action) in traditional RL is identified as the eigen state (eigen action) in QRL. The state (action) set can be represented with a quantum superposition state and the eigen state (eigen action) can be obtained by randomly observing the simulated quantum state according to the collapse postulate of quantum measurement. The probability of the eigen action is determined by the probability amplitude, which is parallelly updated according to rewards. Some related characteristics of QRL such as convergence, optimality and balancing between exploration and exploitation are also analyzed, which shows that this approach makes a good tradeoff between exploration and exploitation using the probability amplitude and can speed up learning through the quantum parallelism. To evaluate the performance and practicability of QRL, several simulated experiments are given and the results demonstrate the effectiveness and superiority of QRL algorithm for some complex problems. The present work is also an effective exploration on the application of quantum computation to artificial intelligence.