Multi-object aerodynamic design optimization using deep reinforcement learning

HIGHLIGHTS

• who: Multi-object aerodynamic design et al. from the School of Aeronautics, Northwestern Polytechnical University, Xi'an, China have published the article: Multi-object aerodynamic design optimization using deep reinforcement learning, in the Journal: (JOURNAL)
• what: In this work a popular RL method called proximal policy optimization (PPO) is proposed to investigate optimization. This approach has been applied in several cases. The authors focused on the Pareto multi-object optimization problem.
• how: Non-dominated sorted genetic algorithm II (NSGA-II)32 found 69 Pareto solutions in 8000 CFD calculations (the detailed results are . . .
  

   

  

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

  Thanks :)

  Username or Email

  Password

  Remember me

  Lost your password?

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