Progress for week 15 (2018)

Fra Robin

(Forskjeller mellom versjoner)
Gå til: navigasjon, søk
(Vetle Bu Solgård)
 
Linje 1: Linje 1:
== Vetle Bu Solgård ==
== Vetle Bu Solgård ==
=== Budget ===
=== Budget ===
-
*  
+
* Finish REINFORCE algorithm
 +
* Finish Test environment
=== Accounting ===
=== Accounting ===
-
*
+
* Finished implementing REINFORCE baseline
 +
* Having some trouble with test environment - Might just validate algorithms in MountaincarContinous env.
 +
* Did a lot of code editing. (Reward signal and state experimentation as well as flow of prog)
== Martin Hovin ==
== Martin Hovin ==

Nåværende revisjon fra 13. apr 2018 kl. 12:24

Innhold

Vetle Bu Solgård

Budget

  • Finish REINFORCE algorithm
  • Finish Test environment

Accounting

  • Finished implementing REINFORCE baseline
  • Having some trouble with test environment - Might just validate algorithms in MountaincarContinous env.
  • Did a lot of code editing. (Reward signal and state experimentation as well as flow of prog)

Martin Hovin

Budget

  • Gjøre ferdig Relearn
  • Skrive om resultater
  • Skrive Diskusjon
  • Skrive konklusjon
  • Legge til evt. nye deler til teoretisk bakgrunn
Personlige verktøy