Bottom-Up Design of Quantum Optical Experiments Using Discrete Generative Models
Designing quantum optical experiments requires searching over discrete circuit topologies and continuous parameters, often with multiple realizations of the same target state. Graph-based methods commonly address this problem by optimizing a dense graph and pruning it toward a single circuit. We introduce \texttt{Grinch}, a bottom-up reward-driven generative framework that learns to sample optical graphs directly from fidelity-based rewards without relying on a pre-existing training dataset. We demonstrate the framework on multipartite entangled states, graph and cluster states, and nonlocal photonic-gate targets, obtaining multiple high-fidelity optical graphs. We identify asymptotic solutions for states that cannot be generated exactly by graphs, as well as nonlocal Toffoli gate constructions requiring two ancillas. Our work presents hardware-constraint objectives, which lead to alternative constructions of CNOT and Toffoli gates when connections between ancilla nodes are restricted. These findings illustrate a reward-driven approach to quantum optical inverse design, exploring alternative circuit topologies while directly incorporating connectivity constraints into the search process.