Reinforcement Learning

AI Methods for Permutation Circuit Synthesis Across Generic Topologies

This paper investigates artificial intelligence (AI) methodologies for the synthesis and transpilation of permutation circuits across generic topologies. Our approach uses Reinforcement Learning (RL) techniques to achieve near-optimal synthesis of …

Quantum Verifiable Rewards for Post-Training Qiskit Code Assistant

Qiskit is an open-source quantum computing framework that allows users to design, simulate, and run quantum circuits on real quantum hardware. We explore post-training techniques for LLMs to assist in writing Qiskit code. We introduce quantum …

Reinforcement learning based transpilation of quantum circuits

Systems and techniques that facilitate quantum circuit transpiling are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can …

Pauli Network Circuit Synthesis with Reinforcement Learning Paper Published

Celebrating the arxiv publication of the Pauli Network Circuit Synthesis with Reinforcement Learning paper. The AI-powered transpiler pass has been available in the Qiskit Transpiler Service since November 2024, as presented at Quantum Developer Conference 2024.

Pauli Network Circuit Synthesis with Reinforcement Learning

We introduce a Reinforcement Learning (RL)-based method for re-synthesis of quantum circuits containing arbitrary Pauli rotations alongside Clifford operations. By collapsing each sub-block to a compact representation and then synthesizing it …

qiskit-ibm-transpiler

AI-powered quantum circuit optimization library — Ranking 3rd in Unitary Foundation 2025 Survey, 929K+ downloads

Qiskit Gym

Reinforcement learning environments for quantum circuit synthesis — powers the AI transpiler passes

Reinforced Learning for Quantum Design

A computer-implemented process for generating a policy for design of quantum devices using a quantum hardware design kit including instructions and parameters associated with the instructions includes the following operations. An environment for a …

Reinforcement Learning based Clifford Circuit Synthesis

Systems and techniques that facilitate Clifford circuit synthesis are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can …

Reinforcement Learning for Quantum Transpiling: Research Paper Published

Published research demonstrating integration of Reinforcement Learning into quantum transpiling workflows for Qiskit transpiler service. Achieves near-optimal circuit synthesis and routing with significant performance improvements over traditional optimization methods, handling Linear Function, Clifford, and Permutation circuits up to 65 qubits.