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:2412.13686 · Quantum Machine Intelligence

A hybrid learning agent for episodic learning tasks with unknown target distance

Oliver Sefrin, Sabine Wölk

Published Apr 11, 2025• 1 citation
arXivHTMLPDF

Abstract

Abstract The “hybrid agent for quantum-accessible reinforcement learning,” as defined in (Hamann and Wölk New J Phys 24:033044 2022), provides a proven quasi-quadratic speedup and is experimentally tested. However, the standard version can only be applied to episodic learning tasks with fixed episode length. In many real-world applications, the information about the necessary number of steps within an episode to reach a defined target is not available in advance and especially before reaching the target for the first time. Furthermore, in such scenarios, classical agents have the advantage of observing at which step they reach the target. How to best deal with an unknown target distance in classical and quantum reinforcement learning and whether the hybrid agent can provide an advantage in such learning scenarios is unknown so far. In this work, we introduce a hybrid agent with a stochastic episode length selection strategy to alleviate the need for knowledge about the necessary episode length. Through simulations, we test the adapted hybrid agent’s performance versus classical counterparts with and without similar episode selection strategies. Our simulations demonstrate a speedup in certain scenarios due to our developed episode length selection strategy for classical learning agents as well as an additional speedup for our resulting hybrid learning agent.

DOI
10.1007/s42484-025-00269-1

Related papers

Extending the Hybrid Agent for Reinforcement Learning Beyond Fixed-Length Scenarios

Sefrin, Oliver, Wölk, Sabine Esther

In Quantum Reinforcement Learning, the "hybrid agent for quantum-accessible reinforcement learning" (Hamann and Wölk, 2022) provides a quadratic speed-up in terms of sample complexity over classical algorithms. This hybrid agent may be used in deterministic and strictly episodic environments, for which the maze problem is a standard example. With the current algorithm, however, the episode length (i.e., the number of actions to be played in an episode) is a hyperparameter which needs to be set. For scenarios such as mazes with an unknown distance towards the goal, this poses a problem, since a feasible episode length value is not known initially. In this work, we propose an adaption to the hybrid algorithm that uses a variable episode length selection strategy, allowing its usage in a wider range of maze problem scenarios. We test our novel approach against classical agents in various maze scenarios. Finally, we reason about conditions for which a quantum advantage persists.

•Mar 1, 2024•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•2 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•15 citations

Exponential improvements for quantum-accessible reinforcement learning

Vedran Dunjko, Yi-Kai Liu, Xingyao Wu +1 more

Quantum computers can offer dramatic improvements over classical devices for data analysis tasks such as prediction and classification. However, less is known about the advantages that quantum computers may bring in the setting of reinforcement learning, where learning is achieved via interaction with a task environment. Here, we consider a special case of reinforcement learning, where the task environment allows quantum access. In addition, we impose certain "naturalness" conditions on the task environment, which rule out the kinds of oracle problems that are studied in quantum query complexity (and for which quantum speedups are well-known). Within this framework of quantum-accessible reinforcement learning environments, we demonstrate that quantum agents can achieve exponential improvements in learning efficiency, surpassing previous results that showed only quadratic improvements. A key step in the proof is to construct task environments that encode well-known oracle problems, such as Simon's problem and Recursive Fourier Sampling, while satisfying the above "naturalness" conditions for reinforcement learning. Our results suggest that quantum agents may perform well in certain game-playing scenarios, where the game has recursive structure, and the agent can learn by playing against itself.

arXiv:1710.11160•Oct 30, 2017•34 citations

Quantum-accessible reinforcement learning beyond strictly epochal environments

A. Hamann, Vedran Dunjko, Sabine Wölk

In recent years, quantum-enhanced machine learning has emerged as a particularly fruitful application of quantum algorithms, covering aspects of supervised, unsupervised and reinforcement learning. Reinforcement learning offers numerous options of how quantum theory can be applied, and is arguably the least explored, from a quantum perspective. Here, an agent explores an environment and tries to find a behavior optimizing some figure of merit. Some of the first approaches investigated settings where this exploration can be sped-up, by considering quantum analogs of classical environments, which can then be queried in superposition. If the environments have a strict periodic structure in time (i.e. are strictly episodic), such environments can be effectively converted to conventional oracles encountered in quantum information. However, in general environments, we obtain scenarios that generalize standard oracle tasks. In this work, we consider one such generalization, where the environment is not strictly episodic, which is mapped to an oracle identification setting with a changing oracle. We analyze this case and show that standard amplitude-amplification techniques can, with minor modifications, still be applied to achieve quadratic speed-ups. In addition, we prove that an algorithm based on Grover iterations is optimal for oracle identification even if the oracle changes over time in a way that the "rewarded space" is monotonically increasing. This result constitutes one of the first generalizations of quantum-accessible reinforcement learning.

arXiv:2008.01481•Quantum Machine Intelligence•Aug 2, 2021•21 citations

Challenge-Response Quantum Reinforcement Learning with Application to Quantum-Assisted Authentication

Jawaher Kaldari, Saif Al-Kuwari

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.

quant-pharXiv:2602.12464•Quantum Machine Intelligence•Feb 16, 2026•1 citation
Abstract The “hybrid agent for quantum-accessible reinforcement learning,” as defined in (Hamann and Wölk New J Phys 24:033044 2022), provides a proven quasi-quadratic speedup and is experimentally tested. However, the standard version can only be applied to episodic learning tasks with fixed episode length. In many real-world applications, the information about the necessary number of steps within an episode to reach a defined target is not available in advance and especially before reaching the target for the first time. Furthermore, in such scenarios, classical agents have the advantage of observing at which step they reach the target. How to best deal with an unknown target distance in classical and quantum reinforcement learning and whether the hybrid agent can provide an advantage in such learning scenarios is unknown so far. In this work, we introduce a hybrid agent with a stochastic episode length selection strategy to alleviate the need for knowledge about the necessary episode length. Through simulations, we test the adapted hybrid agent’s performance versus classical counterparts with and without similar episode selection strategies. Our simulations demonstrate a speedup in certain scenarios due to our developed episode length selection strategy for classical learning agents as well as an additional speedup for our resulting hybrid learning agent.
In Quantum Reinforcement Learning, the "hybrid agent for quantum-accessible reinforcement learning" (Hamann and Wölk, 2022) provides a quadratic speed-up in terms of sample complexity over classical algorithms. This hybrid agent may be used in deterministic and strictly episodic environments, for which the maze problem is a standard example. With the current algorithm, however, the episode length (i.e., the number of actions to be played in an episode) is a hyperparameter which needs to be set. For scenarios such as mazes with an unknown distance towards the goal, this poses a problem, since a feasible episode length value is not known initially. In this work, we propose an adaption to the hybrid algorithm that uses a variable episode length selection strategy, allowing its usage in a wider range of maze problem scenarios. We test our novel approach against classical agents in various maze scenarios. Finally, we reason about conditions for which a quantum advantage persists.
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.
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 computers can offer dramatic improvements over classical devices for data analysis tasks such as prediction and classification. However, less is known about the advantages that quantum computers may bring in the setting of reinforcement learning, where learning is achieved via interaction with a task environment. Here, we consider a special case of reinforcement learning, where the task environment allows quantum access. In addition, we impose certain "naturalness" conditions on the task environment, which rule out the kinds of oracle problems that are studied in quantum query complexity (and for which quantum speedups are well-known). Within this framework of quantum-accessible reinforcement learning environments, we demonstrate that quantum agents can achieve exponential improvements in learning efficiency, surpassing previous results that showed only quadratic improvements. A key step in the proof is to construct task environments that encode well-known oracle problems, such as Simon's problem and Recursive Fourier Sampling, while satisfying the above "naturalness" conditions for reinforcement learning. Our results suggest that quantum agents may perform well in certain game-playing scenarios, where the game has recursive structure, and the agent can learn by playing against itself.
In recent years, quantum-enhanced machine learning has emerged as a particularly fruitful application of quantum algorithms, covering aspects of supervised, unsupervised and reinforcement learning. Reinforcement learning offers numerous options of how quantum theory can be applied, and is arguably the least explored, from a quantum perspective. Here, an agent explores an environment and tries to find a behavior optimizing some figure of merit. Some of the first approaches investigated settings where this exploration can be sped-up, by considering quantum analogs of classical environments, which can then be queried in superposition. If the environments have a strict periodic structure in time (i.e. are strictly episodic), such environments can be effectively converted to conventional oracles encountered in quantum information. However, in general environments, we obtain scenarios that generalize standard oracle tasks. In this work, we consider one such generalization, where the environment is not strictly episodic, which is mapped to an oracle identification setting with a changing oracle. We analyze this case and show that standard amplitude-amplification techniques can, with minor modifications, still be applied to achieve quadratic speed-ups. In addition, we prove that an algorithm based on Grover iterations is optimal for oracle identification even if the oracle changes over time in a way that the "rewarded space" is monotonically increasing. This result constitutes one of the first generalizations of quantum-accessible reinforcement learning.
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.