mlsanityData to 14 Oct 2026

Quantum Boltzmann Machines for Sample-Efficient Reinforcement Learning

arXiv 2511.04856 ↗First posted 6 Nov 2025cs.LG quant-phcited by 0

On the map: Deep reinforcement learning methods → Quantum reinforcement learning

Abstract (arXiv)

We introduce theoretically grounded Continuous Semi-Quantum Boltzmann Machines (CSQBMs) that supports continuous-action reinforcement learning. By combining exponential-family priors over visible units with quantum Boltzmann distributions over hidden units, CSQBMs yield a hybrid quantum-classical model that reduces qubit requirements while retaining strong expressiveness. Crucially, gradients with respect to continuous variables can be computed analytically, enabling direct integration into Actor-Critic algorithms. Building on this, we propose a continuous Q-learning framework that replaces global maximization by efficient sampling from the CSQBM distribution, thereby overcoming instability issues in continuous control.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Quantum reinforcement learning, one of 15 directions in Deep reinforcement learning methods. Builds on 18 of its 49 references that are in the map. First posted on arXiv 6 Nov 2025.

Builds on

18 of 49 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Using Quantum Solved Deep Boltzmann Machines to Increase the Data Efficiency of RL Agents30 Aug

Other references · 17

  1. 2017Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networkscited by 744
  2. 2018QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulationcited by 743
  3. 2016Input Convex Neural Networkscited by 414
  4. 2019Your Classifier is Secretly an Energy Based Model and You Should Treat it Like Onecited by 405
  5. 2016Continuous Deep Q-Learning with Model-based Accelerationcited by 157
  6. 2021Parametrized quantum policies for reinforcement learningcited by 90
  7. 2022A Survey on Quantum Reinforcement Learningcited by 53
  8. 2019CAQL: Continuous Action Q-Learningcited by 23
  9. 2016Reinforcement Learning Using Quantum Boltzmann Machinescited by 20
  10. 2023On the Sample Complexity of Quantum Boltzmann Machine Learningcited by 19
  11. 2019Q-Learning for Continuous Actions with Cross-Entropy Guided Policiescited by 18
  12. 2020Training and Classification using a Restricted Boltzmann Machine on the D-Wave 2000Qcited by 18
5 more
  1. 2022Optimizing Objective Functions from Trained ReLU Neural Networks via Samplingcited by 11
  2. 2014Gaussian-binary Restricted Boltzmann Machines on Modeling Natural Image Statisticscited by 7
  3. 2025Expressive equivalence of classical and quantum restricted Boltzmann machinescited by 7
  4. 2017Free energy-based reinforcement learning using a quantum processorcited by 4
  5. 2022On Quantum Circuits for Discrete Graphical Modelscited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Reinforcement Learning for Quantum Technology
  2. 2024Hamiltonian-based Quantum Reinforcement Learning for Neural Combinatorial Optimization
  3. 2024Trainability issues in quantum policy gradients
  4. 2024Robustness and Generalization in Quantum Reinforcement Learning via Lipschitz Regularization
  5. 2026Quantum vs. Classical Machine Learning: A Unified Empirical Comparison
  6. 2025Quantum Bayesian Networks Can Speed up Reinforcement Learning in Partially Observable Environments
  7. 2026Continuous Quantum Feedback Control via Kraus-Parameterized Belief Reinforcement Learning
  8. 2026Reinforcement learning for quantum processes with memory