Complexity scaling and optimal policy degeneracy in quantum reinforcement learning via analytically solvable unitary-control-then-measure models
We propose and analyse a class of analytically solvable models of quantum reinforcement learning (QRL), formulated as finite-horizon Markov decision processes in finite-dimensional Hilbert spaces. The models are built around a `unitary-control-then-measure' protocol, in which a learning agent applies unitary transformations to a quantum state and interleaves each control step with a projective measurement onto a prescribed reference basis. Exact closed-form expressions for trajectory probabilities, rewards, and the expected return are derived for four concrete realisations: a closed-chain and an anti-periodic qubit implementation, a qutrit model with ladder coupling, and a four-level two-qubit system. Two structural features of these QRL protocols are then analysed. First, we identify and quantify the reduction in the computational complexity of the expected return, from the nominally exponential $O(e^N)$ scaling in the trajectory length~$N$ to an explicit power-law $O(N^{\mathcal{I}})$, driven by two rigorously established mechanisms, a trajectory equivalence and a sparsity of the transition graph, besides a third, conjectured one: a spectral concentration of the return, at the optimal policy, onto the polynomially populated trajectory classes. Second, we characterise the degeneracy of optimal policies. The low-dimensional models exhibit unique optima whose asymptotic behaviour with~$N$ is governed by the quantum Zeno effect, while the four-level system displays both plateau-type quasi-degeneracy at large horizons and genuine discrete degeneracy at critical energy parameters -- phenomena with no counterpart in the measurement-free quantum optimal control landscape.