Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

arXiv:2412.08725

A quantum-classical reinforcement learning model to play Atari games

Dominik Freinberger, Julian Lemmel, Radu Grosu, Sofiène Jerbi

Published Dec 11, 2024• 7 citations
arXivHTMLPDF

Abstract

Recent advances in reinforcement learning have demonstrated the potential of quantum learning models based on parametrized quantum circuits as an alternative to deep learning models. On the one hand, these findings have shown the ultimate exponential speed-ups in learning that full-blown quantum models can offer in certain -- artificially constructed -- environments. On the other hand, they have demonstrated the ability of experimentally accessible PQCs to solve OpenAI Gym benchmarking tasks. However, it remains an open question whether these near-term QRL techniques can be successfully applied to more complex problems exhibiting high-dimensional observation spaces. In this work, we bridge this gap and present a hybrid model combining a PQC with classical feature encoding and post-processing layers that is capable of tackling Atari games. A classical model, subjected to architectural restrictions similar to those present in the hybrid model is constructed to serve as a reference. Our numerical investigation demonstrates that the proposed hybrid model is capable of solving the Pong environment and achieving scores comparable to the classical reference in Breakout. Furthermore, our findings shed light on important hyperparameter settings and design choices that impact the interplay of the quantum and classical components. This work contributes to the understanding of near-term quantum learning models and makes an important step towards their deployment in real-world RL scenarios.

DOI
10.48550/arxiv.2412.08725

Related papers

Playing Atari with Hybrid Quantum-Classical Reinforcement Learning

Owen Lockwood, Mei Si

Despite the successes of recent works in quantum reinforcement learning, there are still severe limitations on its applications due to the challenge of encoding large observation spaces into quantum systems. To address this challenge, we propose using a neural network as a data encoder, with the Atari games as our testbed. Specifically, the neural network converts the pixel input from the games to quantum data for a Quantum Variational Circuit (QVC); this hybrid model is then used as a function approximator in the Double Deep Q Networks algorithm. We explore a number of variations of this algorithm and find that our proposed hybrid models do not achieve meaningful results on two Atari games - Breakout and Pong. We suspect this is due to the significantly reduced sizes of the hybrid quantum-classical systems.

arXiv:2107.04114•Jul 8, 2021•25 citations

Parametrized Quantum Circuits for Reinforcement Learning

Kelvin Tafadzwa Mpofu, Patience T. Mthunzi-Kufa

Research on quantum computing is still in its infancy, but it has a lot of potential uses. One topic with potential is machine learning, namely in the field of reinforcement learning. This work examines the integration of parametrized quantum circuits (PQC) into reinforcement learning (RL) algorithms, assessing the potential of quantum-enhanced models to solve classical RL tasks. It closely follows the example found on the TensorFlow website. This paper reviews applications of quantum reinforcement learning (QRL). We examine PQCs in a standard RL scenario, the CartPole-v1 environment from Gym, using TensorFlow Quantum and Cirq, to evaluate the relative performance of quantum versus conventional models. In comparison to conventional deep neural network (ONN) models, PQCs show slower convergence and higher processing needs, even if they are still able to learn the task and perform competitively. After they are fully trained, the quantum models show unique difficulties during the early training stages and reach a performance stability level like classical methods. This study sheds light on the present constraints as well as possible uses of quantum computing in reinforcement learning, particularly in situations with intricate, high-dimensional settings that prove difficult for classical computers to handle effectively. As we look to the future, we suggest that investigating hybrid quantum-classical algorithms, developing quantum hardware, and using quantum RL for increasingly difficult tasks are essential first steps. The study presents findings from both a classical reinforcement learning algorithm and a quantum integrated reinforcement learning algorithm. To provide a reliable comparison between quantum reinforcement algorithms and their classical equivalents, further work remains. This work lays the groundwork for future advances in the field by investigating the viability and use of quantum algorithms in reinforcement learning, even if it is not particularly unique. The purpose of this work is to help newcomers to this emerging field of study.

International Multidisciplinary Information Technology and Engineering Conference (IMITEC)•Nov 27, 2024•5 citations

Reinforcement Learning with Quantum Variational Circuit

Owen Lockwood, Mei Si

The development of quantum computational techniques has advanced greatly in recent years, parallel to the advancements in techniques for deep reinforcement learning. This work explores the potential for quantum computing to facilitate reinforcement learning problems. Quantum computing approaches offer important potential improvements in time and space complexity over traditional algorithms because of its ability to exploit the quantum phenomena of superposition and entanglement. Specifically, we investigate the use of quantum variational circuits, a form of quantum machine learning. We present our techniques for encoding classical data for a quantum variational circuit, we further explore pure and hybrid quantum algorithms for DQN and Double DQN. Our results indicate both hybrid and pure quantum variational circuit have the ability to solve reinforcement learning tasks with a smaller parameter space. These comparison are conducted with two OpenAI Gym environments: CartPole and Blackjack, The success of this work is indicative of a strong future relationship between quantum machine learning and deep reinforcement learning.

arXiv:2008.07524•Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment•Oct 1, 2020•170 citations

Unentangled quantum reinforcement learning agents in the OpenAI Gym

Jen-Yueh Hsiao, Yuxuan Du, Wei-Yin Chiang +2 more

Classical reinforcement learning (RL) has generated excellent results in different regions; however, its sample inefficiency remains a critical issue. In this paper, we provide concrete numerical evidence that the sample efficiency (the speed of convergence) of quantum RL could be better than that of classical RL, and for achieving comparable learning performance, quantum RL could use much (at least one order of magnitude) fewer trainable parameters than classical RL. Specifically, we employ the popular benchmarking environments of RL in the OpenAI Gym, and show that our quantum RL agent converges faster than classical fully-connected neural networks (FCNs) in the tasks of CartPole and Acrobot under the same optimization process. We also successfully train the first quantum RL agent that can complete the task of LunarLander in the OpenAI Gym. Our quantum RL agent only requires a single-qubit-based variational quantum circuit without entangling gates, followed by a classical neural network (NN) to post-process the measurement output. Finally, we could accomplish the aforementioned tasks on the real IBM quantum machines. To the best of our knowledge, none of the earlier quantum RL agents could do that.

arXiv:2203.14348•Mar 27, 2022•34 citations

Dissecting Quantum Reinforcement Learning: A Systematic Evaluation of Key Components

Javier Lazaro, Juan-Ignacio Vazquez, Pablo Garcia-Bringas

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.

quant-pharXiv:2511.17112•Nov 24, 2025•1 citation

Quantum Deep Reinforcement Learning for Robot Navigation Tasks

Hans Hohenfeld, Dirk Heimann, Felix Wiebe +1 more

We utilize hybrid quantum deep reinforcement learning to learn navigation tasks for a simple, wheeled robot in simulated environments of increasing complexity. For this, we train parameterized quantum circuits (PQCs) with two different encoding strategies in a hybrid quantum-classical setup as well as a classical neural network baseline with the double deep Q network (DDQN) reinforcement learning algorithm. Quantum deep reinforcement learning (QDRL) has previously been studied in several relatively simple benchmark environments, mainly from the OpenAI gym suite. However, scaling behavior and applicability of QDRL to more demanding tasks closer to real-world problems e.g., from the robotics domain, have not been studied previously. Here, we show that quantum circuits in hybrid quantum-classic reinforcement learning setups are capable of learning optimal policies in multiple robotic navigation scenarios with notably fewer trainable parameters compared to a classical baseline. Across a large number of experimental configurations, we find that the employed quantum circuits outperform the classical neural network baselines when equating for the number of trainable parameters. Yet, the classical neural network consistently showed better results concerning training times and stability, with at least one order of magnitude of trainable parameters more than the best-performing quantum circuits. However, validating the robustness of the learning methods in a large and dynamic environment, we find that the classical baseline produces more stable and better performing policies overall. For the two encoding schemes, we observed better results for consecutively encoding the classical state vector on each qubit compared to encoding each component on a separate qubit. Our findings demonstrate that current hybrid quantum machine-learning approaches can be scaled to simple robotic problems while yielding sufficient results, at least in an idealized simulated setting, but there are yet open questions regarding the application to considerably more demanding tasks. We anticipate that our work will contribute to introducing quantum machine learning in general and quantum deep reinforcement learning in particular to more demanding problem domains and emphasize the importance of encoding techniques for classic data in hybrid quantum-classical settings.

arXiv:2202.12180•IEEE Access•Jan 1, 2024•76 citations
Recent advances in reinforcement learning have demonstrated the potential of quantum learning models based on parametrized quantum circuits as an alternative to deep learning models. On the one hand, these findings have shown the ultimate exponential speed-ups in learning that full-blown quantum models can offer in certain -- artificially constructed -- environments. On the other hand, they have demonstrated the ability of experimentally accessible PQCs to solve OpenAI Gym benchmarking tasks. However, it remains an open question whether these near-term QRL techniques can be successfully applied to more complex problems exhibiting high-dimensional observation spaces. In this work, we bridge this gap and present a hybrid model combining a PQC with classical feature encoding and post-processing layers that is capable of tackling Atari games. A classical model, subjected to architectural restrictions similar to those present in the hybrid model is constructed to serve as a reference. Our numerical investigation demonstrates that the proposed hybrid model is capable of solving the Pong environment and achieving scores comparable to the classical reference in Breakout. Furthermore, our findings shed light on important hyperparameter settings and design choices that impact the interplay of the quantum and classical components. This work contributes to the understanding of near-term quantum learning models and makes an important step towards their deployment in real-world RL scenarios.
Despite the successes of recent works in quantum reinforcement learning, there are still severe limitations on its applications due to the challenge of encoding large observation spaces into quantum systems. To address this challenge, we propose using a neural network as a data encoder, with the Atari games as our testbed. Specifically, the neural network converts the pixel input from the games to quantum data for a Quantum Variational Circuit (QVC); this hybrid model is then used as a function approximator in the Double Deep Q Networks algorithm. We explore a number of variations of this algorithm and find that our proposed hybrid models do not achieve meaningful results on two Atari games - Breakout and Pong. We suspect this is due to the significantly reduced sizes of the hybrid quantum-classical systems.
Research on quantum computing is still in its infancy, but it has a lot of potential uses. One topic with potential is machine learning, namely in the field of reinforcement learning. This work examines the integration of parametrized quantum circuits (PQC) into reinforcement learning (RL) algorithms, assessing the potential of quantum-enhanced models to solve classical RL tasks. It closely follows the example found on the TensorFlow website. This paper reviews applications of quantum reinforcement learning (QRL). We examine PQCs in a standard RL scenario, the CartPole-v1 environment from Gym, using TensorFlow Quantum and Cirq, to evaluate the relative performance of quantum versus conventional models. In comparison to conventional deep neural network (ONN) models, PQCs show slower convergence and higher processing needs, even if they are still able to learn the task and perform competitively. After they are fully trained, the quantum models show unique difficulties during the early training stages and reach a performance stability level like classical methods. This study sheds light on the present constraints as well as possible uses of quantum computing in reinforcement learning, particularly in situations with intricate, high-dimensional settings that prove difficult for classical computers to handle effectively. As we look to the future, we suggest that investigating hybrid quantum-classical algorithms, developing quantum hardware, and using quantum RL for increasingly difficult tasks are essential first steps. The study presents findings from both a classical reinforcement learning algorithm and a quantum integrated reinforcement learning algorithm. To provide a reliable comparison between quantum reinforcement algorithms and their classical equivalents, further work remains. This work lays the groundwork for future advances in the field by investigating the viability and use of quantum algorithms in reinforcement learning, even if it is not particularly unique. The purpose of this work is to help newcomers to this emerging field of study.
The development of quantum computational techniques has advanced greatly in recent years, parallel to the advancements in techniques for deep reinforcement learning. This work explores the potential for quantum computing to facilitate reinforcement learning problems. Quantum computing approaches offer important potential improvements in time and space complexity over traditional algorithms because of its ability to exploit the quantum phenomena of superposition and entanglement. Specifically, we investigate the use of quantum variational circuits, a form of quantum machine learning. We present our techniques for encoding classical data for a quantum variational circuit, we further explore pure and hybrid quantum algorithms for DQN and Double DQN. Our results indicate both hybrid and pure quantum variational circuit have the ability to solve reinforcement learning tasks with a smaller parameter space. These comparison are conducted with two OpenAI Gym environments: CartPole and Blackjack, The success of this work is indicative of a strong future relationship between quantum machine learning and deep reinforcement learning.
Classical reinforcement learning (RL) has generated excellent results in different regions; however, its sample inefficiency remains a critical issue. In this paper, we provide concrete numerical evidence that the sample efficiency (the speed of convergence) of quantum RL could be better than that of classical RL, and for achieving comparable learning performance, quantum RL could use much (at least one order of magnitude) fewer trainable parameters than classical RL. Specifically, we employ the popular benchmarking environments of RL in the OpenAI Gym, and show that our quantum RL agent converges faster than classical fully-connected neural networks (FCNs) in the tasks of CartPole and Acrobot under the same optimization process. We also successfully train the first quantum RL agent that can complete the task of LunarLander in the OpenAI Gym. Our quantum RL agent only requires a single-qubit-based variational quantum circuit without entangling gates, followed by a classical neural network (NN) to post-process the measurement output. Finally, we could accomplish the aforementioned tasks on the real IBM quantum machines. To the best of our knowledge, none of the earlier quantum RL agents could do that.
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.
We utilize hybrid quantum deep reinforcement learning to learn navigation tasks for a simple, wheeled robot in simulated environments of increasing complexity. For this, we train parameterized quantum circuits (PQCs) with two different encoding strategies in a hybrid quantum-classical setup as well as a classical neural network baseline with the double deep Q network (DDQN) reinforcement learning algorithm. Quantum deep reinforcement learning (QDRL) has previously been studied in several relatively simple benchmark environments, mainly from the OpenAI gym suite. However, scaling behavior and applicability of QDRL to more demanding tasks closer to real-world problems e.g., from the robotics domain, have not been studied previously. Here, we show that quantum circuits in hybrid quantum-classic reinforcement learning setups are capable of learning optimal policies in multiple robotic navigation scenarios with notably fewer trainable parameters compared to a classical baseline. Across a large number of experimental configurations, we find that the employed quantum circuits outperform the classical neural network baselines when equating for the number of trainable parameters. Yet, the classical neural network consistently showed better results concerning training times and stability, with at least one order of magnitude of trainable parameters more than the best-performing quantum circuits. However, validating the robustness of the learning methods in a large and dynamic environment, we find that the classical baseline produces more stable and better performing policies overall. For the two encoding schemes, we observed better results for consecutively encoding the classical state vector on each qubit compared to encoding each component on a separate qubit. Our findings demonstrate that current hybrid quantum machine-learning approaches can be scaled to simple robotic problems while yielding sufficient results, at least in an idealized simulated setting, but there are yet open questions regarding the application to considerably more demanding tasks. We anticipate that our work will contribute to introducing quantum machine learning in general and quantum deep reinforcement learning in particular to more demanding problem domains and emphasize the importance of encoding techniques for classic data in hybrid quantum-classical settings.