Reinforcement Learning (RL) has been gaining significant attention in recent years as a powerful tool for solving complex control problems. This paper presents a possible application of an RL algorithm called deep Q-network (DQN) to the speed-tracking control of a DC motor. The proposed approach opens up new possibilities for the application of RL in the control of DC motors and other dynamic systems since it proposes a direct RL controller able to drive the motor in a realistic and fully randomized scenario.

A Reinforcement Learning based controller for optimal speed control of a DC motor using deep Q-network algorithm

Rossi Federico;Gruosso G.;storti Gajani G.
2023-01-01

Abstract

Reinforcement Learning (RL) has been gaining significant attention in recent years as a powerful tool for solving complex control problems. This paper presents a possible application of an RL algorithm called deep Q-network (DQN) to the speed-tracking control of a DC motor. The proposed approach opens up new possibilities for the application of RL in the control of DC motors and other dynamic systems since it proposes a direct RL controller able to drive the motor in a realistic and fully randomized scenario.
2023
EUROCON 2023 - 20th International Conference on Smart Technologies, Proceedings
978-1-6654-6397-3
DC motor
PID controller
Reinforcement Learning
speed control
File in questo prodotto:
File Dimensione Formato  
pp3.pdf

Accesso riservato

Descrizione: articolo
: Publisher’s version
Dimensione 1.21 MB
Formato Adobe PDF
1.21 MB Adobe PDF   Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11311/1258360
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 3
  • ???jsp.display-item.citation.isi??? ND
social impact