Quantum RL

RL: Reinforcement Learning

Quantum reinforcement learning explores both using quantum methods to build learning agents and using reinforcement learning to control quantum systems. Common approaches include parameterized quantum circuits as policy or value models, hybrid training with classical methods such as PPO and SAC, and quantum subroutines for estimation, search, or optimization. Applications range from quantum-state preparation, feedback control, and circuit synthesis to routing, finance, and network scheduling. The central open question is when these methods provide a genuine advantage: theoretical speedups can depend on environment structure, while empirical gains are uneven and must be weighed against noise, hardware costs, scalability, and strong classical baselines.

Latest papers

34 papers2 papers in the last four weeks, down 60% on the four weeks before. 0.0% of all new papers.

Reinforcement learning for quantum processes with memory
Mar 26, 2026Josep Lumbreras, Ruo Cheng Huang, Yanglin Hu +2Quantum RL Regret Minimization in RL
Nanyang Quantum Hub, School of Physical and Mathematical Sciences, Nanyang Technological University, Singapore · Centre for Quantum Technologies, Nanyang Technological University, Singapore · QICI Quantum Information and Computation Initiative, School of Computing and Data Science, The University of Hong Kong, Pokfulam Road, Hong Kong SAR, China +2
Quantum entanglement provides a competitive advantage in adversarial games
Mar 11, 2026Peiyong Wang, Kieran Hymas, James QuachQuantum RL Quantum Machine Learning
Technology, CSIRO Clayton, Research Way, Clayton, VIC 3168, Australia.
Reinforcement Learning for Parameterized Quantum State Preparation: A Comparative Study
Feb 18, 2026Gerhard Stenzel, Isabella Debelic, Michael Kölle +4Quantum Circuit Synthesis Quantum State Preparation
LMU Munich Department of Computer Science Chair of Mobile and Distributed Systems
Quantum Bayesian Networks Can Speed up Reinforcement Learning in Partially Observable Environments
Jul 24, 2025Gilberto Cunha, Alexandra Ramôa, André Sequeira +2Partially Observable RL Bayesian RL
High-Assurance Software Laboratory (HASLab), INESC TEC, Portugal · Department of Computer Science, University of Minho, Portugal · International Iberian Nanotechnology Laboratory (INL), Portugal

Mar 26, 2026J/K move · Enter open · S save

Reinforcement learning for quantum processes with memory

Josep Lumbreras, Ruo Cheng Huang, Yanglin Hu, Marco Fanizza+1

Nanyang Quantum Hub, School of Physical and Mathematical Sciences, Nanyang Technological University, Singapore · Centre for Quantum Technologies, Nanyang Technological University, Singapore · QICI Quantum Information and Computation Initiative, School of Computing and Data Science, The University of Hong Kong, Pokfulam Road, Hong Kong SAR, China+2

Quantum RL Regret Minimization in RL Quantum System Identification

Open paper AskPDF arXiv

In reinforcement learning, an agent interacts sequentially with an environment to maximize a reward, receiving only partial, probabilistic feedback. This creates a fundamental exploration-exploitation trade-off: the agent must explore to learn the hidden dynamics while exploiting this knowledge to maximize its target objective. While extensively studied classically, applying this framework to quantum systems requires dealing with hidden quantum states that evolve via unknown dynamics. We formalize this problem via a framework where the environment maintains a hidden quantum memory evolving via unknown quantum channels, and the agent intervenes sequentially using quantum instruments. For this setting, we adapt an optimistic maximum-likelihood estimation algorithm. We extend the analysis to continuous action spaces, allowing us to model general positive operator-valued measures (POVMs). By controlling the propagation of estimation errors through quantum channels and instruments, we prove that the cumulative regret of our strategy scales as

\widetilde{\mathcal{O}}(\sqrt{K})

over

K

episodes. Furthermore, via a reduction to the multi-armed quantum bandit problem, we establish information-theoretic lower bounds demonstrating that this sublinear scaling is strictly optimal up to polylogarithmic factors. As a physical application, we consider state-agnostic work extraction. When extracting free energy from a sequence of non-i.i.d. quantum states correlated by a hidden memory, any lack of knowledge about the source leads to thermodynamic dissipation. In our setting, the mathematical regret exactly quantifies this cumulative dissipation. Using our adaptive algorithm, the agent uses past energy outcomes to improve its extraction protocol on the fly, achieving sublinear cumulative dissipation, and, consequently, an asymptotically zero dissipation rate.

Latest papers

Reinforcement learning for quantum processes with memory

Quantum entanglement provides a competitive advantage in adversarial games

Reinforcement Learning for Parameterized Quantum State Preparation: A Comparative Study

Quantum Bayesian Networks Can Speed up Reinforcement Learning in Partially Observable Environments