Deep reinforcement learning for feedback control in a collective flashing ratchet

Abstract

A collective flashing ratchet transports Brownian particles using a spatially periodic, asymmetric, and time-dependent on-off switchable potential. The net current of the particles in this system can be substantially increased by feedback control based on the particle positions. Several feedback policies for maximizing the current have been proposed, but optimal policies have not been found for a moderate number of particles. Here, we use deep reinforcement learning (RL) to find optimal policies, with results showing that policies built with a suitable neural network architecture outperform the previous policies. Moreover, even in a time-delayed feedback situation where the on-off switching of the potential is delayed, we demonstrate that the policies provided by deep RL provide higher currents than the previous strategies.

6 + 4 pages, 3 + 2 figures

References in corpus (11)

• Thermodynamics of feedback controlled systems
• Feedback control in a collective flashing ratchet
• Deep Reinforcement Learning for Quantum Gate Control
• Realization of a feedback controlled flashing ratchet
• Fluctuation-Driven Molecular Transport in an Asymmetric Membrane Channel
• Time-Delayed Feedback control of a flashing ratchet
• Effect of time delay on feedback control of a flashing ratchet
• Information and flux in a feedback controlled Brownian ratchet
• Rocking feedback controlled ratchets
• Threshold feedback control for a collective flashing ratchet: threshold dependence
• Optimal operation of feedback flashing ratchets