Learning Quantum Circuits with RL Agents: QCircuit-v1

less than 1 minute read

Published:

In this post we keep exploring the integration of IBM qiskit, a library developed to design, run and simulate quantum circuits, and OpenAI gym, a library developed to define, train and run reinforcement learning agents.

We still rely on the quantum game, qcircuit, that we presented in a previous blogpost. This time we consider a more complex version of the game, where the player has to interact with a bigger quantum circuit, and has to reach a more challenging ending state.

As before, we deploy some pre-made agents made available in the stable-baselines library, and train them on our quantum game. We then observe and compare the performance of these agents against the performance of a random agent.

Notebook here