WIth an unbelievably great team of collaborators: @wwdabney, @Mesnard_Thomas, Bilal Piot, Mo Azar, Nicolas Heess, @hado, Greg Wayne, Satinder Singh, Doina Precup, and Remi Munos 
-
-
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
-
-
This looks amazing, by the way is there a reason why the notation for the return is Z instead of G
I wonder if that was somehow inspired by the pseudo termination reward z in the Horde paper. -
Ha, nice link, love that paper! We went with the distributional RL notation train here, but maybe it's worth to have a table somewhere mapping all the numerous RL notation to the same place...
- Još 2 druga odgovora
Novi razgovor -
-
-
Nice paper Anna, I love your writing style :)
- Kraj razgovora
Novi razgovor -
-
-
Which poster session?
-
Pm today! :)
Kraj razgovora
Novi razgovor -
-
-
Just read this paper. One comment is given the Markov chain treatment I kept wanting for some discussions relating state evolutions for differentiating between ergodicity and non-ergodic evolutions, given the hindsight treatment the latter I suspect are now measurable. Cheers.
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
Čini se da učitavanje traje već neko vrijeme.
Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.

