A quantum-classical reinforcement learning model to play Atari games

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Freinberger, Dominik, Lemmel, Julian, Grosu, Radu, Jerbi, Sofiene
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910742182100992
author Freinberger, Dominik
Lemmel, Julian
Grosu, Radu
Jerbi, Sofiene
author_facet Freinberger, Dominik
Lemmel, Julian
Grosu, Radu
Jerbi, Sofiene
contents Recent advances in reinforcement learning have demonstrated the potential of quantum learning models based on parametrized quantum circuits as an alternative to deep learning models. On the one hand, these findings have shown the ultimate exponential speed-ups in learning that full-blown quantum models can offer in certain -- artificially constructed -- environments. On the other hand, they have demonstrated the ability of experimentally accessible PQCs to solve OpenAI Gym benchmarking tasks. However, it remains an open question whether these near-term QRL techniques can be successfully applied to more complex problems exhibiting high-dimensional observation spaces. In this work, we bridge this gap and present a hybrid model combining a PQC with classical feature encoding and post-processing layers that is capable of tackling Atari games. A classical model, subjected to architectural restrictions similar to those present in the hybrid model is constructed to serve as a reference. Our numerical investigation demonstrates that the proposed hybrid model is capable of solving the Pong environment and achieving scores comparable to the classical reference in Breakout. Furthermore, our findings shed light on important hyperparameter settings and design choices that impact the interplay of the quantum and classical components. This work contributes to the understanding of near-term quantum learning models and makes an important step towards their deployment in real-world RL scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2412_08725
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A quantum-classical reinforcement learning model to play Atari games
Freinberger, Dominik
Lemmel, Julian
Grosu, Radu
Jerbi, Sofiene
Quantum Physics
Artificial Intelligence
Machine Learning
Recent advances in reinforcement learning have demonstrated the potential of quantum learning models based on parametrized quantum circuits as an alternative to deep learning models. On the one hand, these findings have shown the ultimate exponential speed-ups in learning that full-blown quantum models can offer in certain -- artificially constructed -- environments. On the other hand, they have demonstrated the ability of experimentally accessible PQCs to solve OpenAI Gym benchmarking tasks. However, it remains an open question whether these near-term QRL techniques can be successfully applied to more complex problems exhibiting high-dimensional observation spaces. In this work, we bridge this gap and present a hybrid model combining a PQC with classical feature encoding and post-processing layers that is capable of tackling Atari games. A classical model, subjected to architectural restrictions similar to those present in the hybrid model is constructed to serve as a reference. Our numerical investigation demonstrates that the proposed hybrid model is capable of solving the Pong environment and achieving scores comparable to the classical reference in Breakout. Furthermore, our findings shed light on important hyperparameter settings and design choices that impact the interplay of the quantum and classical components. This work contributes to the understanding of near-term quantum learning models and makes an important step towards their deployment in real-world RL scenarios.
title A quantum-classical reinforcement learning model to play Atari games
topic Quantum Physics
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2412.08725