Decision-making and control with diffractive optical networks

HIGHLIGHTS

• What: The authors propose using deep reinforcement learning to implement DONs that imitate human-level decisionmaking and control capability. Advanced Photonics Nexus To address the complexity of imitating human players on the optical platform, the authors develop the training framework of policy and network shown in Fig 1(d), using a combination of novel and existing general-purpose techniques for neural_network architectures. The approach lowers the bar for the polarization state of light, and partially polarized light can be used in the network. The authors evaluate the dependence of the prediction accuracy on the number of hidden . . .
  

   

  

  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.