Quantum Boltzmann Machines for Sample-Efficient Reinforcement Learning
This work addresses sample efficiency and instability in continuous control for reinforcement learning practitioners, representing a novel method for a known bottleneck rather than a foundational breakthrough.
The paper tackles the problem of sample-efficient reinforcement learning in continuous-action settings by introducing Continuous Semi-Quantum Boltzmann Machines (CSQBMs), which combine quantum and classical elements to reduce qubit requirements and enable analytical gradient computation, resulting in a stable continuous Q-learning framework that overcomes instability issues.
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.