Quantum Reinforcement Learning

TLDR

Machine learning in unknown probabilistic environments relies on new representations and computational mechanisms. The paper proposes a novel quantum reinforcement learning method that integrates quantum theory with reinforcement learning. The method models states and actions as quantum superposition eigenstates, updates probability amplitudes via rewards using a value‑updating algorithm, and selects actions through quantum measurement collapse. Experiments demonstrate that QRL converges, balances exploration and exploitation, and outperforms classical approaches on complex tasks, confirming its effectiveness and potential for quantum‑enhanced AI.

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.