Optimizing cascaded control of mechatronic systems through constrained residual reinforcement learning

HIGHLIGHTS

• who: Tom Staessens et al. from the Department of Electrical Energy, Metals, Mechanical Constructions and Systems, Ghent University have published the paper: Optimizing Cascaded Control of Mechatronic Systems through Constrained Residual Reinforcement Learning, in the Journal: Machines 2023, 11, 402. of /2023/
• what: The authors propose constrained residual reinforcement learning (RL) an intuitive method that allows to improve the performance of a control structure while maintaining safe operation at all times. Next the authors propose a novel actor structure to enable efficient learning under the setting. The authors show that the standard algorithm is suboptimal . . .
  

   

  

  If you want to have access to all the content you need to log in!

  Thanks :)

  Username or E-mail:

  If you don't have an account, you can create one here.