A quantum-classical reinforcement learning model to play Atari games

• URL: http://arxiv.org/abs/2412.08725v1
• Date: Wed, 11 Dec 2024 19:00:09 GMT
• Title: A quantum-classical reinforcement learning model to play Atari games
• Authors: Dominik Freinberger, Julian Lemmel, Radu Grosu, Sofiene Jerbi,
• Abstract summary: Recent advances in reinforcement learning have demonstrated the potential of quantum learning models based on parametrized quantum circuits. We present a hybrid model combining a PQC with classical feature encoding and post-processing layers that is capable of tackling Atari games. 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.
• Score: 6.302177333213775
• License:
• Abstract: 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.

Related papers

• Hybrid Quantum-Classical Reinforcement Learning in Latent Observation Spaces [0.36944296923226316]
  Recent progress in quantum machine learning has sparked interest in using quantum methods to tackle classical control problems. We propose to solve this dimensionality challenge by a classical autoencoder and a quantum agent together. A series of numerical experiments are designed for a performance analysis of the latent-space learning method.
  arXiv  Detail & Related papers  (2024-10-23T21:19:38Z)
• Hybrid Classical-Quantum architecture for vectorised image classification of hand-written sketches [0.0]
  Quantum machine learning investigates how quantum phenomena can be exploited to learn data in an alternative way. Recent advances indicate that hybrid classical-quantum models can attain competitive performances at low architecture complexities. Here, we introduce vector-based representation of sketch drawings as a test-bed for QML models.
  arXiv  Detail & Related papers  (2024-07-08T21:51:20Z)
• Practicality of training a quantum-classical machine in the NISQ era [0.0]
  This study explores the limits of training a real experimental quantum classical hybrid system using supervised training protocols, on an ion trap platform. Challenges associated with ion trap-coupled classical processors are addressed, highlighting the $robustness$ of the genetic algorithm as a classical in navigating the noisy channels of NISQ-devices. These findings contribute insights into the performance of quantum-classical hybrid systems, emphasizing the significance of efficient training strategies and hardware considerations for practical quantum machine learning applications.
  arXiv  Detail & Related papers  (2024-01-22T16:27:14Z)
• A Framework for Demonstrating Practical Quantum Advantage: Racing Quantum against Classical Generative Models [62.997667081978825]
  We build over a proposed framework for evaluating the generalization performance of generative models. We establish the first comparative race towards practical quantum advantage (PQA) between classical and quantum generative models. Our results suggest that QCBMs are more efficient in the data-limited regime than the other state-of-the-art classical generative models.
  arXiv  Detail & Related papers  (2023-03-27T22:48:28Z)
• SEQUENT: Towards Traceable Quantum Machine Learning using Sequential Quantum Enhanced Training [5.819818547073678]
  We propose an improved architecture and training process for the traceable application of quantum computing methods to hybrid machine learning. We provide formal evidence for the disadvantage of current methods and preliminary experimental results as a proof-of-concept for the applicability of SEQUENT.
  arXiv  Detail & Related papers  (2023-01-06T16:55:59Z)
• Quantum Reinforcement Learning for Solving a Stochastic Frozen Lake Environment and the Impact of Quantum Architecture Choices [0.0]
  Quantum reinforcement learning (QRL) models augment classical reinforcement learning schemes with quantum-enhanced kernels. Different proposals on how to construct such models empirically show a promising performance. It is however unclear how these quantum-enhanced kernels as subroutines within a reinforcement learning pipeline need to be constructed to indeed result in an improved performance.
  arXiv  Detail & Related papers  (2022-12-15T16:08:31Z)
• A didactic approach to quantum machine learning with a single qubit [68.8204255655161]
  We focus on the case of learning with a single qubit, using data re-uploading techniques. We implement the different proposed formulations in toy and real-world datasets using the qiskit quantum computing SDK.
  arXiv  Detail & Related papers  (2022-11-23T18:25:32Z)
• A Quantum Kernel Learning Approach to Acoustic Modeling for Spoken Command Recognition [69.97260364850001]
  We propose a quantum kernel learning (QKL) framework to address the inherent data sparsity issues. We project acoustic features based on classical-to-quantum feature encoding.
  arXiv  Detail & Related papers  (2022-11-02T16:46:23Z)
• Recent Advances for Quantum Neural Networks in Generative Learning [98.88205308106778]
  Quantum generative learning models (QGLMs) may surpass their classical counterparts. We review the current progress of QGLMs from the perspective of machine learning. We discuss the potential applications of QGLMs in both conventional machine learning tasks and quantum physics.
  arXiv  Detail & Related papers  (2022-06-07T07:32:57Z)
• When BERT Meets Quantum Temporal Convolution Learning for Text Classification in Heterogeneous Computing [75.75419308975746]
  This work proposes a vertical federated learning architecture based on variational quantum circuits to demonstrate the competitive performance of a quantum-enhanced pre-trained BERT model for text classification. Our experiments on intent classification show that our proposed BERT-QTC model attains competitive experimental results in the Snips and ATIS spoken language datasets.
  arXiv  Detail & Related papers  (2022-02-17T09:55:21Z)
• Experimental Quantum Generative Adversarial Networks for Image Generation [93.06926114985761]
  We experimentally achieve the learning and generation of real-world hand-written digit images on a superconducting quantum processor. Our work provides guidance for developing advanced quantum generative models on near-term quantum devices.
  arXiv  Detail & Related papers  (2020-10-13T06:57:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.