Reinforcement Learning for Adaptive Composition of Quantum Circuit Optimisation Passes
This addresses the challenge of designing effective optimization sequences for quantum circuits, which is incremental as it applies an existing method (reinforcement learning) to a specific domain problem.
The paper tackles the problem of optimizing quantum circuit performance by using reinforcement learning to adaptively compose optimization passes, achieving a mean two-qubit gate reduction of 57.7% compared to 41.8% for the best default sequence.
Many quantum software development kits provide a suite of circuit optimisation passes. These passes have been highly optimised and tested in isolation. However, the order in which they are applied is left to the user, or else defined in general-purpose default pass sequences. While general-purpose sequences miss opportunities for optimisation which are particular to individual circuits, designing pass sequences bespoke to particular circuits requires exceptional knowledge about quantum circuit design and optimisation. Here we propose and demonstrate training a reinforcement learning agent to compose optimisation-pass sequences. In particular the agent's action space consists of passes for two-qubit gate count reduction used in default PyTKET pass sequences. For the circuits in our diverse test set, the (mean, median) fraction of two-qubit gates removed by the agent is $(57.7\%, \ 56.7 \%)$, compared to $(41.8 \%, \ 50.0 \%)$ for the next best default pass sequence.