{"ID":2845556,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.04856","arxiv_id":"2511.04856","title":"Quantum Boltzmann Machines for Sample-Efficient Reinforcement Learning","abstract":"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.","short_abstract":"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 qub...","url_abs":"https://arxiv.org/abs/2511.04856","url_pdf":"https://arxiv.org/pdf/2511.04856v1","authors":"[\"Thore Gerlach\",\"Michael Schenk\",\"Verena Kain\"]","published":"2025-11-06T22:40:18Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"quant-ph\"]","methods":"[\"Reinforcement Learning\"]","has_code":false}