Selective network discovery via deep reinforcement learning on embedded spaces

HIGHLIGHTS

• who: Peter Morales from the MIT Lincoln Laboratory, Lexington, USA have published the article: Selective network discovery via deep reinforcement learning on embedded spaces, in the Journal: (JOURNAL)
• what: The authors propose a framework called net‑ work actor critic (NAC) which learns a policy and notion of future reward in an offline setting via a deep reinforcement learning algorithm. The authors show that offline models of reward and network discovery policies lead to significantly improved performance when compared to competitive online discovery algorithms. The authors show that, for a variety of complex learning scenarios, the . . .
  

   

  

  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.