Quantum Reinforcement Learning (QRL) is an emerging field with many novel approaches suitable for noisy intermediate-scale quantum (NISQ) devices being proposed recently. Projective Simulation (PS) is a classical machine learning method based on random walks in a Directed Acyclic Graph (DAG), and is mainly used to train agents in a Reinforcement Learning setup. This graph corresponds to the Episodic Compositional Memory (ECM) of the agent. For the quantum version of PS we use quantum walks of single photons in quantum optical circuits, which go through tunable components (beamsplitters and phase shifters). We call this specific model Quantum Optical Projective Simulation (QOPS). In this work, we propose a general framework to translate any 2-layer ECM to a quantum optical circuit and an algorithm for solving quantum strategic games using QOPS. Moreover, we introduce QOPS with an entangled state as input. The application that we are using to evaluate the performance of the framework is the Prisoner's Dilemma. We executed the implementation using Altair's noisy simulator, designed to emulate a single photon-based quantum processor by Quandela. The algorithm provided promising results even in the presence of noise, which makes it a strong candidate for runs on single-photon-based quantum processors.
Quantum Reinforcement Learning (QRL) is an emerging field with many novel approaches suitable for noisy intermediate-scale quantum (NISQ) devices being proposed recently. Projective Simulation (PS) is a classical machine learning method based on random walks in a Directed Acyclic Graph (DAG), and is mainly used to train agents in a Reinforcement Learning setup. This graph corresponds to the Episodic Compositional Memory (ECM) of the agent. For the quantum version of PS we use quantum walks of single photons in quantum optical circuits, which go through tunable components (beamsplitters and phase shifters). We call this specific model Quantum Optical Projective Simulation (QOPS). In this work, we propose a general framework to translate any 2-layer ECM to a quantum optical circuit and an algorithm for solving quantum strategic games using QOPS. Moreover, we introduce QOPS with an entangled state as input. The application that we are using to evaluate the performance of the framework is the Prisoner's Dilemma. We executed the implementation using Altair's noisy simulator, designed to emulate a single photon-based quantum processor by Quandela. The algorithm provided promising results even in the presence of noise, which makes it a strong candidate for runs on single-photon-based quantum processors.
Variational quantum algorithms show potential in effectively operating on noisy intermediate-scale quantum devices. A variational approach to reinforcement learning has been recently proposed, incorporating linear-optical interferometers and a classical learning model known as projective simulation (PS). PS is a decision-making tool for reinforcement learning and can be classically represented as a random walk on a graph that describes the agent's memory. In its optical quantum version, this approach utilizes quantum walks of single photons on a mesh of tunable beamsplitters and phase shifters to select actions. In this work, we present the implementation of this algorithm on Ascella, a single-photon-based quantum computer from Quandela. The focus is drawn on solving a test bed task to showcase the potential of the quantum agent with respect to the classical agent. Published by the American Physical Society 2024
Abstract Quantum machine learning (QML) is a young but rapidly growing field where quantum information meets machine learning. Here, we will introduce a new QML model generalising the classical concept of reinforcement learning to the quantum domain, i.e. quantum reinforcement learning (QRL). In particular, we apply this idea to the maze problem, where an agent has to learn the optimal set of actions in order to escape from a maze with the highest success probability. To perform the strategy optimisation, we consider a hybrid protocol where QRL is combined with classical deep neural networks. In particular, we find that the agent learns the optimal strategy in both the classical and quantum regimes, and we also investigate its behaviour in a noisy environment. It turns out that the quantum speedup does robustly allow the agent to exploit useful actions also at very short time scales, with key roles played by the quantum coherence and the external noise. This new framework has the high potential to be applied to perform different tasks (e.g. high transmission/processing rates and quantum error correction) in the new-generation noisy intermediate-scale quantum (NISQ) devices whose topology engineering is starting to become a new and crucial control knob for practical applications in real-world problems. This work is dedicated to the memory of Peter Wittek.
Abstract Variational quantum algorithms represent a promising approach to quantum machine learning where classical neural networks are replaced by parametrized quantum circuits. However, both approaches suffer from a clear limitation, that is a lack of interpretability. Here, we present a variational method to quantize projective simulation (PS), a reinforcement learning model aimed at interpretable artificial intelligence. Decision making in PS is modeled as a random walk on a graph describing the agent’s memory. To implement the quantized model, we consider quantum walks of single photons in a lattice of tunable Mach–Zehnder interferometers trained via variational algorithms. Using an example from transfer learning, we show that the quantized PS model can exploit quantum interference to acquire capabilities beyond those of its classical counterpart. Finally, we discuss the role of quantum interference for training and tracing the decision making process, paving the way for realizations of interpretable quantum learning agents.
Parameterised quantum circuit (PQC) based Quantum Reinforcement Learning (QRL) has emerged as a promising paradigm at the intersection of quantum computing and reinforcement learning (RL). By design, PQCs create hybrid quantum-classical models, but their practical applicability remains uncertain due to training instabilities, barren plateaus (BPs), and the difficulty of isolating the contribution of individual pipeline components. In this work, we dissect PQC based QRL architectures through a systematic experimental evaluation of three aspects recurrently identified as critical: (i) data embedding strategies, with Data Reuploading (DR) as an advanced approach; (ii) ansatz design, particularly the role of entanglement; and (iii) post-processing blocks after quantum measurement, with a focus on the underexplored Output Reuse (OR) technique. Using a unified PPO-CartPole framework, we perform controlled comparisons between hybrid and classical agents under identical conditions. Our results show that OR, though purely classical, exhibits distinct behaviour in hybrid pipelines, that DR improves trainability and stability, and that stronger entanglement can degrade optimisation, offsetting classical gains. Together, these findings provide controlled empirical evidence of the interplay between quantum and classical contributions, and establish a reproducible framework for systematic benchmarking and component-wise analysis in QRL.
Quantum Reinforcement Learning (QRL) represents a novel approach to reinforcement learning that leverages the unique capabilities of quantum computing to enhance learning efficiency and enable the exploration of complex behavioral rules. This paper explores the theoretical foundations, design principles, and potential applications of a QRL algorithm, focusing on its ability to learn intricate patterns and make superior decisions within challenging environments. The core mechanism centers around quantum superposition and entanglement, strategically employed to represent the state space and guide the agent's exploration, resulting in improved learning speed and robustness. We present a detailed framework for implementing this algorithm, discussing its potential impact on diverse reinforcement learning scenarios, particularly those encountered in edge applications. The paper concludes with a discussion of ongoing research directions and future prospects for QRL.
Quantum reinforcement learning (QRL) has emerged as a promising research direction that integrates quantum information processing into reinforcement learning frameworks. While many existing QRL studies apply quantum agents to classical environments, it has been realized that the potential advantages of QRL are most naturally explored in environments that exhibit intrinsically quantum characteristics, where the agent's observations and interactions arise from quantum processes. In this work, we propose a quantum reinforcement learning environment formulated as a challenge-response task with hidden information. In the proposed environment, Alice encodes a classical bit into the parameters of a quantum circuit, while Bob, with a trained reinforcement learning agent, interacts with a limited number of quantum state copies to infer the hidden bit. The agent must select measurement strategies and decide when to terminate the interaction under explicit resource constraints. To study the solvability of the proposed environment, we consider three agents: a purely classical agent, a lightweight hybrid agent and a deep hybrid agent. Through experiments, we analyze the trade-off between inference accuracy and quantum resource consumption under varying interaction penalties. Our results show that the lightweight hybrid agent achieves reliable inference using as few as two quantum state copies, outperforming both the classical baseline and the deep hybrid agent across both high and low-penalty regimes. We further evaluate robustness under realistic quantum noise models and discuss the relevance of the proposed environment for security-oriented applications, including quantum-assisted authentication.