Machine learning applications in quantum state engineering

Firstly, we implement a classical reinforcement- learning inspired approach to achieve closed loop quantum control of 3-level systems. Our results show that this technique can effectively design optimal control pulses resulting in near- perfect transfer in non-standard but practically relevant operating regimes.

Such results are considered in the case of an abstract 3-level system but we discuss a scenario where said control can be used to directly entangle qubits coupled via a common resonator. Following this we employ a genetic-algorithm-based optimization in larger resonator-mediated multi-qubit systems to show that heuristic search techniques can be used to find optimal driving fields in complex, composite quantum systems.