Intrinsically motivated exploration of learned goal spaces

HIGHLIGHTS

• who: Adrien Laversanne-Finot from the UnivBordeaux and Ensta ParisTech, Paris, France have published the article: Intrinsically Motivated Exploration of Learned Goal Spaces, in the Journal: (JOURNAL)
• what: To apply the ideas developed in Pu00e9ru00e9 et_al to a real-world robotic setup with limited computing resources (raspberry Pi 3), the authors focus on population based IMGEPs. Ideally, to make the approach as simple and as general as possible, such a goal space should be learned from observations gathered by the agent during exploration. The authors focus on Variational Autoencoders (VAEs).
• how: For the . . .
  

   

  

  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.