Model bias is an inherent limitation of the current dominant approach to optimal quantum control, which relies on a system simulation for optimization of control policies. To overcome this limitation, we propose a circuit-based approach for training a reinforcement learning agent on quantum control tasks in a model-free way. Given a continuously parameterized control circuit, the agent learns its parameters through trial-and-error interaction with the quantum system, using measurements as the only source of information about the quantum state. By focusing on the task of quantum state preparation in a harmonic oscillator coupled to an ancilla qubit, we show how to reward the learning agent using measurements of experimentally available observables. We demonstrate by numerical simulations preparation of arbitrary states using both open- and closed-loop control through adaptive quantum feedback. Our work is of immediate relevance to superconducting circuits and trapped ions platforms where such training can be implemented real-time in an experiment, allowing complete elimination of model bias and the adaptation of quantum control policies to the specific system in which they are deployed.
Download