Staged Hybridisation for Visual Quantum Reinforcement Learning via Knowledge Distillation
For researchers in quantum reinforcement learning, this work provides a practical method to circumvent the difficulty of end-to-end training of VQCs on visual tasks, though the improvements are incremental.
The paper proposes a staged knowledge distillation strategy for visual quantum reinforcement learning, where a classical teacher's frozen encoder is used to train compact VQC-based heads, enabling shallow quantum policies to achieve near-teacher performance on CartPole Pixels and Acrobot Pixels.
Visual environments are a demanding setting for quantum reinforcement learning (QRL): high-dimensional observations, unstable RL optimisation, and constrained variational quantum circuits (VQCs) are difficult to train jointly. This paper studies knowledge distillation (KD) as a staged hybridisation strategy for visual QRL. Instead of training a hybrid visual agent end-to-end from pixels, we first train a classical visual teacher, freeze its encoder as a feature interface, and distil the teacher's policy behaviour into compact downstream heads. These heads can be classical or VQC-based, enabling small quantum-compatible students to be evaluated under the same frozen representation as compact classical controls. We evaluate the pipeline on CartPole Pixels and Acrobot Pixels. The results show that staged KD enables shallow VQC heads to acquire non-trivial visual-control behaviour in settings where direct pixel-based training would be substantially more difficult. Angle-encoded VQC heads retain near-teacher performance, while amplitude-encoded heads push compactness to an extreme regime, at the cost of greater fragility, stronger budget sensitivity, and higher simulation time. Overall, staged KD reframes visual QRL as a compact-head learning problem, opening a practical route for training small quantum-compatible policies outside the standard end-to-end RL loop.