Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

arXiv:1706.00074

Free energy-based reinforcement learning using a quantum processor

Anna Levit, Daniel Crawford, Navid Ghadermarzy, Jaspreet S. Oberoi, Ehsan Zahedinejad, Pooya Ronagh

Published May 29, 2017• 16 citations
arXivHTMLPDF

Abstract

Recent theoretical and experimental results suggest the possibility of using current and near-future quantum hardware in challenging sampling tasks. In this paper, we introduce free energy-based reinforcement learning (FERL) as an application of quantum hardware. We propose a method for processing a quantum annealer's measured qubit spin configurations in approximating the free energy of a quantum Boltzmann machine (QBM). We then apply this method to perform reinforcement learning on the grid-world problem using the D-Wave 2000Q quantum annealer. The experimental results show that our technique is a promising method for harnessing the power of quantum sampling in reinforcement learning tasks.

DOI
10.48550/arxiv.1706.00074

Related papers

Reinforcement Learning via Replica Stacking of Quantum Measurements for the Training of Quantum Boltzmann Machines

Anna Levit, Daniel Crawford, Navid Ghadermarzy +3 more

Recent theoretical and experimental results suggest the possibility of using current and near-future quantum hardware in challenging sampling tasks. In this paper, we introduce free-energy-based reinforcement learning (FERL) as an application of quantum hardware. We propose a method for processing a quantum annealer’s measured qubit spin configurations in approximating the free energy of a quantum Boltzmann machine (QBM). We then apply this method to perform reinforcement learning on the grid-world problem using the D-Wave 2000Q quantum annealer. The experimental results show that our technique is a promising method for harnessing the power of quantum sampling in reinforcement learning tasks.

•Feb 15, 2018•0 citations

Reinforcement learning using quantum Boltzmann machines

Daniel Crawford, Anna Levit, Navid Ghadermarzy +2 more

We investigate whether quantum annealers with select chip layouts can outperform classical computers in reinforcement learning tasks. We associate a transverse field Ising spin Hamiltonian with a layout of qubits similar to that of a deep Boltzmann machine (DBM) and use simulated quantum annealing (SQA) to numerically simulate quantum sampling from this system. We design a reinforcement learning algorithm in which the set of visible nodes representing the states and actions of an optimal policy are the first and last layers of the deep network. In absence of a transverse field, our simulations show that DBMs are trained more effectively than restricted Boltzmann machines (RBM) with the same number of nodes. We then develop a framework for training the network as a quantum Boltzmann machine (QBM) in the presence of a significant transverse field for reinforcement learning. This method also outperforms the reinforcement learning method that uses RBMs.

Quantum Information and Computation•Feb 1, 2018•72 citations

Reinforcement Learning Using Quantum Boltzmann Machines

Crawford, Daniel, Anna Levit, Navid Ghadermarzy +2 more

We investigate whether quantum annealers with select chip layouts can outperform classical computers in reinforcement learning tasks. We associate a transverse field Ising spin Hamiltonian with a layout of qubits similar to that of a deep Boltzmann machine (DBM) and use simulated quantum annealing (SQA) to numerically simulate quantum sampling from this system. We design a reinforcement learning algorithm in which the set of visible nodes representing the states and actions of an optimal policy are the first and last layers of the deep network. In absence of a transverse field, our simulations show that DBMs are trained more effectively than restricted Boltzmann machines (RBM) with the same number of nodes. We then develop a framework for training the network as a quantum Boltzmann machine (QBM) in the presence of a significant transverse field for reinforcement learning. This method also outperforms the reinforcement learning method that uses RBMs.

arXiv:1612.05695•Dec 17, 2016•14 citations

Quantum Reinforcement Learning

Daniel Crawford, Anna Levit, Navid Ghadermarzy +2 more

We investigate whether quantum annealers with select chip layouts can outperform classical computers in reinforcement learning tasks. We associate a transverse field Ising spin Hamiltonian with a layout of qubits similar to that of a deep Boltzmann machine (DBM) and use simulated quantum annealing (SQA) to numerically simulate quantum sampling from this system. We design a reinforcement learning algorithm in which the set of visible nodes representing the states and actions of an optimal policy are the first and last layers of the deep network. In absence of a transverse field, our simulations show that DBMs are trained more effectively than restricted Boltzmann machines (RBM) with the same number of nodes. We then develop a framework for training the network as a quantum Boltzmann machine (QBM) in the presence of a significant transverse field for reinforcement learning. This method also outperforms the reinforcement learning method that uses RBMs.

•Dec 17, 2016•0 citations

Implementació del QAOA en un algoritme de aprenentatge per reforç quàntic aplicat a les línies de feix al CERN

Nicolau Orell, Sebastià

Quantum reinforcement learning (QRL), a cutting-edge field at the intersection of quantum computing and artificial intelligence, has the potential to revolutionize domains like chemistry and autonomous systems with its computational advantages. The free energy-based reinforcement learning algorithm (FERL) is a QRL algorithm inspired by the classical deep Q-learning algorithm (DQN) which uses a quantum Boltzmann machine (QBM) as the Q-function with quantum annealing (QA) as the solver. It has demonstrated considerable advantage compared to its classical counterpart DQN. The aim of this project is exploring the replacement of QA with the quantum approximate optimization algorithm (QAOA) and its recursive variant (RQAOA). We focus on the one-dimensional beam target steering control task based on the beam optics of the TT24-T4 transfer line at CERN. We perform and compare simulations of QA and QAOA, obtaining successful results for both QAOA and RQAOA, noticing that the performance of FERL using RQAOA for p=1 as a solver is very similar to the obtained through simulated QA for this scenario. The success of this experiment might lead the application of the QAOA solver to the hybrid actor-critic algorithm in development at CERN which allows to tackle control tasks using a continuous action space.

•Sep 14, 2023•0 citations

Hybrid actor-critic algorithm for quantum reinforcement learning at CERN beam lines

Michael Schenk, Elías F. Combarro, Michele Grossi +4 more

Abstract Free energy-based reinforcement learning (FERL) with clamped quantum Boltzmann machines (QBM) was shown to significantly improve the learning efficiency compared to classical Q-learning with the restriction, however, to discrete state-action space environments. In this paper, the FERL approach is extended to multi-dimensional continuous state-action space environments to open the doors for a broader range of real-world applications. First, free energy-based Q-learning is studied for discrete action spaces, but continuous state spaces and the impact of experience replay on sample efficiency is assessed. In a second step, a hybrid actor-critic (A-C) scheme for continuous state-action spaces is developed based on the deep deterministic policy gradient algorithm combining a classical actor network with a QBM-based critic. The results obtained with quantum annealing (QA), both simulated and with D-Wave QA hardware, are discussed, and the performance is compared to classical reinforcement learning methods. The environments used throughout represent existing particle accelerator beam lines at the European Organisation for Nuclear Research. Among others, the hybrid A-C agent is evaluated on the actual electron beam line of the Advanced Wakefield Experiment (AWAKE).

arXiv:2209.11044•Quantum Science and Technology•Feb 5, 2024•19 citations
Recent theoretical and experimental results suggest the possibility of using current and near-future quantum hardware in challenging sampling tasks. In this paper, we introduce free energy-based reinforcement learning (FERL) as an application of quantum hardware. We propose a method for processing a quantum annealer's measured qubit spin configurations in approximating the free energy of a quantum Boltzmann machine (QBM). We then apply this method to perform reinforcement learning on the grid-world problem using the D-Wave 2000Q quantum annealer. The experimental results show that our technique is a promising method for harnessing the power of quantum sampling in reinforcement learning tasks.
Recent theoretical and experimental results suggest the possibility of using current and near-future quantum hardware in challenging sampling tasks. In this paper, we introduce free-energy-based reinforcement learning (FERL) as an application of quantum hardware. We propose a method for processing a quantum annealer’s measured qubit spin configurations in approximating the free energy of a quantum Boltzmann machine (QBM). We then apply this method to perform reinforcement learning on the grid-world problem using the D-Wave 2000Q quantum annealer. The experimental results show that our technique is a promising method for harnessing the power of quantum sampling in reinforcement learning tasks.
We investigate whether quantum annealers with select chip layouts can outperform classical computers in reinforcement learning tasks. We associate a transverse field Ising spin Hamiltonian with a layout of qubits similar to that of a deep Boltzmann machine (DBM) and use simulated quantum annealing (SQA) to numerically simulate quantum sampling from this system. We design a reinforcement learning algorithm in which the set of visible nodes representing the states and actions of an optimal policy are the first and last layers of the deep network. In absence of a transverse field, our simulations show that DBMs are trained more effectively than restricted Boltzmann machines (RBM) with the same number of nodes. We then develop a framework for training the network as a quantum Boltzmann machine (QBM) in the presence of a significant transverse field for reinforcement learning. This method also outperforms the reinforcement learning method that uses RBMs.
We investigate whether quantum annealers with select chip layouts can outperform classical computers in reinforcement learning tasks. We associate a transverse field Ising spin Hamiltonian with a layout of qubits similar to that of a deep Boltzmann machine (DBM) and use simulated quantum annealing (SQA) to numerically simulate quantum sampling from this system. We design a reinforcement learning algorithm in which the set of visible nodes representing the states and actions of an optimal policy are the first and last layers of the deep network. In absence of a transverse field, our simulations show that DBMs are trained more effectively than restricted Boltzmann machines (RBM) with the same number of nodes. We then develop a framework for training the network as a quantum Boltzmann machine (QBM) in the presence of a significant transverse field for reinforcement learning. This method also outperforms the reinforcement learning method that uses RBMs.
We investigate whether quantum annealers with select chip layouts can outperform classical computers in reinforcement learning tasks. We associate a transverse field Ising spin Hamiltonian with a layout of qubits similar to that of a deep Boltzmann machine (DBM) and use simulated quantum annealing (SQA) to numerically simulate quantum sampling from this system. We design a reinforcement learning algorithm in which the set of visible nodes representing the states and actions of an optimal policy are the first and last layers of the deep network. In absence of a transverse field, our simulations show that DBMs are trained more effectively than restricted Boltzmann machines (RBM) with the same number of nodes. We then develop a framework for training the network as a quantum Boltzmann machine (QBM) in the presence of a significant transverse field for reinforcement learning. This method also outperforms the reinforcement learning method that uses RBMs.
Quantum reinforcement learning (QRL), a cutting-edge field at the intersection of quantum computing and artificial intelligence, has the potential to revolutionize domains like chemistry and autonomous systems with its computational advantages. The free energy-based reinforcement learning algorithm (FERL) is a QRL algorithm inspired by the classical deep Q-learning algorithm (DQN) which uses a quantum Boltzmann machine (QBM) as the Q-function with quantum annealing (QA) as the solver. It has demonstrated considerable advantage compared to its classical counterpart DQN. The aim of this project is exploring the replacement of QA with the quantum approximate optimization algorithm (QAOA) and its recursive variant (RQAOA). We focus on the one-dimensional beam target steering control task based on the beam optics of the TT24-T4 transfer line at CERN. We perform and compare simulations of QA and QAOA, obtaining successful results for both QAOA and RQAOA, noticing that the performance of FERL using RQAOA for p=1 as a solver is very similar to the obtained through simulated QA for this scenario. The success of this experiment might lead the application of the QAOA solver to the hybrid actor-critic algorithm in development at CERN which allows to tackle control tasks using a continuous action space.
Abstract Free energy-based reinforcement learning (FERL) with clamped quantum Boltzmann machines (QBM) was shown to significantly improve the learning efficiency compared to classical Q-learning with the restriction, however, to discrete state-action space environments. In this paper, the FERL approach is extended to multi-dimensional continuous state-action space environments to open the doors for a broader range of real-world applications. First, free energy-based Q-learning is studied for discrete action spaces, but continuous state spaces and the impact of experience replay on sample efficiency is assessed. In a second step, a hybrid actor-critic (A-C) scheme for continuous state-action spaces is developed based on the deep deterministic policy gradient algorithm combining a classical actor network with a QBM-based critic. The results obtained with quantum annealing (QA), both simulated and with D-Wave QA hardware, are discussed, and the performance is compared to classical reinforcement learning methods. The environments used throughout represent existing particle accelerator beam lines at the European Organisation for Nuclear Research. Among others, the hybrid A-C agent is evaluated on the actual electron beam line of the Advanced Wakefield Experiment (AWAKE).