© 2026 Aqora Quantum S.A.S.

Terms Privacy Legal Notice

Quantum Nanophotonic Materials, Devices, and Systems

Quantum speed-ups in reinforcement learning

Valeria Saggio, Beate E. Asenbeck, Arne Hamann, Teodor Strömberg, Peter Schiansky, Vedran Dunjko, Nicolai Friis, Nicholas C. Harris, Michael J. Hochberg, Dirk Englund, Sabine Wölk, Hans J. Briegel, Philip John Walther

Published Jul 30, 2021• 4 citations

Abstract

As the field of artificial intelligence is pushed forward, the question arises of how fast autonomous machines can learn. Within artificial intelligence, an important paradigm is reinforcement learning, where agents - learning entities capable of decision making - interact with the world they are placed in, called an environment. Thanks to these interactions, agents receive feedback from the environment and thus progressively adjust their behaviour to accomplish a given goal. An important question in reinforcement learning is how fast agents can learn to fulfill their tasks. To answer this question we consider a novel reinforcement learning framework where quantum mechanics is used. In particular, we quantize the agent and the environment and grant them the possibility to also interact quantum-mechanically, that is, by using a quantum channel for their communication. We demonstrate that this feature enables a speed-up in the agent's learning process, and we further show that combining this scenario with classical communication enables the evaluation of such an improvement. This learning protocol is implemented on an integrated re-programmable photonic platform interfaced with photons at telecommunication wavelengths. Thanks to the full tunability of the device, this platform proves the best candidate for the implementation of learning protocols, where a continuous update of the learning process is required.

DOI: 10.1117/12.2593720

Related papers

Experimental Quantum-enhanced Reinforcement Learning

Valeria Saggio, Beate E. Asenbeck, A. Hamann +10 more

In reinforcement learning, a key question for applications is how fast agents can learn. By introducing an agent capable of interacting classically as well as quantum-mechanically with its environment, we experimentally prove that a speed-up in the agent’s learning time is possible.

Photonics in Switching and Computing (PSC)•Jan 1, 2021•0 citations

Quantum Policy Gradient Algorithms

Sofiène Jerbi, Arjan Cornelissen, Māris Ozols +1 more

Understanding the power and limitations of quantum access to data in machine learning tasks is primordial to assess the potential of quantum computing in artificial intelligence. Previous works have already shown that speed-ups in learning are possible when given quantum access to reinforcement learning environments. Yet, the applicability of quantum algorithms in this setting remains very limited, notably in environments with large state and action spaces. In this work, we design quantum algorithms to train state-of-the-art reinforcement learning policies by exploiting quantum interactions with an environment. However, these algorithms only offer full quadratic speed-ups in sample complexity over their classical analogs when the trained policies satisfy some regularity conditions. Interestingly, we find that reinforcement learning policies derived from parametrized quantum circuits are well-behaved with respect to these conditions, which showcases the benefit of a fully-quantum reinforcement learning framework.

arXiv:2212.09328•Leibniz international proceedings in informatics•Dec 19, 2022•8 citations

Performance analysis of a hybrid agent for quantum-accessible reinforcement learning

Arne Hamann, Sabine Wölk

Abstract In the last decade quantum machine learning has provided fascinating and fundamental improvements to supervised, unsupervised and reinforcement learning (RL). In RL, a so-called agent is challenged to solve a task given by some environment. The agent learns to solve the task by exploring the environment and exploiting the rewards it gets from the environment. For some classical task environments, an analogue quantum environment can be constructed which allows to find rewards quadratically faster by applying quantum algorithms. In this paper, we analytically analyze the behavior of a hybrid agent which combines this quadratic speedup in exploration with the policy update of a classical agent. This leads to a faster learning of the hybrid agent compared to the classical agent. We demonstrate that if the classical agent needs on average ⟨J⟩ rewards and ⟨T⟩cl epochs to learn how to solve the task, the hybrid agent will take ⟨ T ⟩ q ⩽ α s α o ⟨ T ⟩ c l ⟨ J ⟩ epochs on average. Here, α s and α o denote constants depending on details of the quantum search and are independent of the problem size. Additionally, we prove that if the environment allows for maximally α o k max sequential coherent interactions, e.g. due to noise effects, an improvement given by ⟨T⟩q ≈ α o ⟨T⟩cl/(4k max) is still possible.

arXiv:2107.14001•New Journal of Physics•Mar 1, 2022•11 citations

Quantum Reinforcement Learning with Quantum Photonics

Lucas Lamata

Quantum machine learning has emerged as a promising paradigm that could accelerate machine learning calculations. Inside this field, quantum reinforcement learning aims at designing and building quantum agents that may exchange information with their environment and adapt to it, with the aim of achieving some goal. Different quantum platforms have been considered for quantum machine learning and specifically for quantum reinforcement learning. Here, we review the field of quantum reinforcement learning and its implementation with quantum photonics. This quantum technology may enhance quantum computation and communication, as well as machine learning, via the fruitful marriage between these previously unrelated fields.

Photonics•Jan 28, 2021•24 citations

Quantum Machine Learning: A Reinforcement Learning Framework

Jincheng Zhang

Quantum Machine Learning (QML) represents a paradigm shift in machine learning, leveraging quantum mechanical principles to accelerate computation and potentially unlock new algorithms. This paper investigates a novel reinforcement learning (RL) framework, termed "Adaptive Neural Network Reinforcement Learning" (ANNR), which employs dynamic parameter adjustment within a self-adaptive neural network to enhance learning efficiency and generalization capabilities. We demonstrate that this approach overcomes limitations of traditional RL methods, offering a promising path towards more robust and adaptable reinforcement learning agents. The core mechanism focuses on iteratively refining neural network weights through a feedback loop, enabling the system to explore complex environments effectively. The research explores the impact of parameter adjustment on both training speed and final performance across various RL tasks.

•Aug 31, 2026•0 citations

Quantum reinforcement learning in dynamic environments

Oliver Sefrin, Manuel Radons, Lars Simon +1 more

Combining quantum computing techniques in the form of amplitude amplification with classical reinforcement learning has led to the so-called “hybrid agent for quantum-accessible reinforcement learning”, which achieves a quadratic speedup in sample complexity for certain learning problems. So far, this hybrid agent has only been applied to stationary learning problems, that is, learning problems without any time dependency within components of the Markov decision process. In this work, we investigate the applicability of the hybrid agent to dynamic RL environments and thus to more realistic scenarios. To this end, we enhance the hybrid agent by introducing a dissipation mechanism and, with the resulting learning agent, perform an empirical comparison with a classical RL agent in an RL environment with a time-dependent reward function. Our findings suggest that the modified hybrid agent can adapt its behavior to changes in the environment quickly, leading to a higher average success probability compared to its classical counterpart.

arXiv:2507.01691•Quantum Machine Intelligence•May 12, 2026•0 citations

As the field of artificial intelligence is pushed forward, the question arises of how fast autonomous machines can learn. Within artificial intelligence, an important paradigm is reinforcement learning, where agents - learning entities capable of decision making - interact with the world they are placed in, called an environment. Thanks to these interactions, agents receive feedback from the environment and thus progressively adjust their behaviour to accomplish a given goal. An important question in reinforcement learning is how fast agents can learn to fulfill their tasks. To answer this question we consider a novel reinforcement learning framework where quantum mechanics is used. In particular, we quantize the agent and the environment and grant them the possibility to also interact quantum-mechanically, that is, by using a quantum channel for their communication. We demonstrate that this feature enables a speed-up in the agent's learning process, and we further show that combining this scenario with classical communication enables the evaluation of such an improvement. This learning protocol is implemented on an integrated re-programmable photonic platform interfaced with photons at telecommunication wavelengths. Thanks to the full tunability of the device, this platform proves the best candidate for the implementation of learning protocols, where a continuous update of the learning process is required.

Understanding the power and limitations of quantum access to data in machine learning tasks is primordial to assess the potential of quantum computing in artificial intelligence. Previous works have already shown that speed-ups in learning are possible when given quantum access to reinforcement learning environments. Yet, the applicability of quantum algorithms in this setting remains very limited, notably in environments with large state and action spaces. In this work, we design quantum algorithms to train state-of-the-art reinforcement learning policies by exploiting quantum interactions with an environment. However, these algorithms only offer full quadratic speed-ups in sample complexity over their classical analogs when the trained policies satisfy some regularity conditions. Interestingly, we find that reinforcement learning policies derived from parametrized quantum circuits are well-behaved with respect to these conditions, which showcases the benefit of a fully-quantum reinforcement learning framework.

Abstract In the last decade quantum machine learning has provided fascinating and fundamental improvements to supervised, unsupervised and reinforcement learning (RL). In RL, a so-called agent is challenged to solve a task given by some environment. The agent learns to solve the task by exploring the environment and exploiting the rewards it gets from the environment. For some classical task environments, an analogue quantum environment can be constructed which allows to find rewards quadratically faster by applying quantum algorithms. In this paper, we analytically analyze the behavior of a hybrid agent which combines this quadratic speedup in exploration with the policy update of a classical agent. This leads to a faster learning of the hybrid agent compared to the classical agent. We demonstrate that if the classical agent needs on average ⟨J⟩ rewards and ⟨T⟩cl epochs to learn how to solve the task, the hybrid agent will take ⟨ T ⟩ q ⩽ α s α o ⟨ T ⟩ c l ⟨ J ⟩ epochs on average. Here, α s and α o denote constants depending on details of the quantum search and are independent of the problem size. Additionally, we prove that if the environment allows for maximally α o k max sequential coherent interactions, e.g. due to noise effects, an improvement given by ⟨T⟩q ≈ α o ⟨T⟩cl/(4k max) is still possible.

Quantum machine learning has emerged as a promising paradigm that could accelerate machine learning calculations. Inside this field, quantum reinforcement learning aims at designing and building quantum agents that may exchange information with their environment and adapt to it, with the aim of achieving some goal. Different quantum platforms have been considered for quantum machine learning and specifically for quantum reinforcement learning. Here, we review the field of quantum reinforcement learning and its implementation with quantum photonics. This quantum technology may enhance quantum computation and communication, as well as machine learning, via the fruitful marriage between these previously unrelated fields.

Quantum Machine Learning (QML) represents a paradigm shift in machine learning, leveraging quantum mechanical principles to accelerate computation and potentially unlock new algorithms. This paper investigates a novel reinforcement learning (RL) framework, termed "Adaptive Neural Network Reinforcement Learning" (ANNR), which employs dynamic parameter adjustment within a self-adaptive neural network to enhance learning efficiency and generalization capabilities. We demonstrate that this approach overcomes limitations of traditional RL methods, offering a promising path towards more robust and adaptable reinforcement learning agents. The core mechanism focuses on iteratively refining neural network weights through a feedback loop, enabling the system to explore complex environments effectively. The research explores the impact of parameter adjustment on both training speed and final performance across various RL tasks.

Combining quantum computing techniques in the form of amplitude amplification with classical reinforcement learning has led to the so-called “hybrid agent for quantum-accessible reinforcement learning”, which achieves a quadratic speedup in sample complexity for certain learning problems. So far, this hybrid agent has only been applied to stationary learning problems, that is, learning problems without any time dependency within components of the Markov decision process. In this work, we investigate the applicability of the hybrid agent to dynamic RL environments and thus to more realistic scenarios. To this end, we enhance the hybrid agent by introducing a dissipation mechanism and, with the resulting learning agent, perform an empirical comparison with a classical RL agent in an RL environment with a time-dependent reward function. Our findings suggest that the modified hybrid agent can adapt its behavior to changes in the environment quickly, leading to a higher average success probability compared to its classical counterpart.