Model-free optimization of power/efficiency tradeoffs in quantum thermal machines using reinforcement learning

Abstract

A quantum thermal machine is an open quantum system that enables the conversion between heat and work at the micro or nano-scale. Optimally controlling such out-of-equilibrium systems is a crucial yet challenging task with applications to quantum technologies and devices. We introduce a general model-free framework based on Reinforcement Learning to identify out-of-equilibrium thermodynamic cycles that are Pareto optimal trade-offs between power and efficiency for quantum heat engines and refrigerators. The method does not require any knowledge of the quantum thermal machine, nor of the system model, nor of the quantum state. Instead, it only observes the heat fluxes, so it is both applicable to simulations and experimental devices. We test our method on a model of an experimentally realistic refrigerator based on a superconducting qubit, and on a heat engine based on a quantum harmonic oscillator. In both cases, we identify the Pareto-front representing optimal power-efficiency tradeoffs, and the corresponding cycles. Such solutions outperform previous proposals made in the literature, such as optimized Otto cycles, reducing quantum friction.

7+13 pages, 9 figures. arXiv admin note: text overlap with arXiv:2108.13525

References in corpus (14)

• Thermodynamic uncertainty relation for biomolecular processes
• Quantum Thermodynamic Cycles and quantum heat engines
• Single ion heat engine with maximum efficiency at maximum power
• Nonequilibrium fluctuations in quantum heat engines: Theory, example, and possible solid state experiments
• Otto refrigerator based on a superconducting qubit: classical and quantum performance
• Deep Reinforcement Learning for Quantum Gate Control
• Quantum Performance of Thermal Machines over Many Cycles
• Thermoelectric conversion at 30K in InAs/InP nanowire quantum dots
• Non-Markov Enhancement of Maximum Power for Quantum Thermal Machines
• Speeding-up a quantum refrigerator via counter-diabatic driving
• Dynamical heat engines with non--Markovian reservoirs
• Two-Stroke Optimization Scheme for Mesoscopic Refrigerators
• Control of Stochastic Quantum Dynamics by Differentiable Programming
• Geometric Bounds on the Power of Adiabatic Thermal Machines

Cited by in corpus (8)

• Reinforcement learning optimization of the charging of a Dicke quantum battery
• Artificial Intelligence for Quantum Computing
• Optimal Thermometers with Spin Networks
• Dissipation-induced collective advantage of a quantum thermal machine
• Experimental graybox quantum system identification and control
• Exploring the Optimal Cycle for Quantum Heat Engine using Reinforcement Learning
• Artificially intelligent Maxwell's demon for optimal control of open quantum systems
• Machine learning delta-T noise for temperature bias estimation