Archives: [ cm / sci / v / y ]
  • /sci/ - Science & Math
    • Index
    • Archives
    • /cm/ - Cute/Male
    • /sci/ - Science & Math
    • /v/ - Video Games (Archive)
    • /y/ - Yaoi
  • Index
    • By Post
    • By Thread
  • Ghost
  • Gallery
Your latest searches
  • /sci/: [image] QLkhFcD1pJYV4bPQikqtdg
  • /sci/: [image] xh9u2dWpKcwlNaLSXcETAw
  • /sci/: [image] f97LGN2cFoIyGEe_aXfwpQ
  • /sci/: [image] VwFSdPCVHduA_JS-sPK-cw
  • /sci/: [image] s8GGIQ-liQLUVBlJZeks6g
Capcode
Show Posts
Deleted Posts
Ghost Posts
Post Type
Results
Order
108KiB, 1238x881, screenshot_938.png
View SameGoogleiqdbSauceNAO
Anonymous Sun 07 Nov 11:28:20 2021 No.13828211 ViewReplyOriginalReport
Quoted By:
What's the current SOTA for reinforcement learning?

Is PPO the best we can do right now? Why haven't there been any advances since 2017?
×

FoolFuuka Imageboard 2.2.0 - Asagi Fetcher
Change Theme
  • Yotsubatwo - Yotsuba
  • Yotsubatwo - Yotsuba B
  • FoolFuuka - Default
  • FoolFuuka - Midnight
  • Fuuka
Change Language
  • English
  • French
  • Italian
  • Portuguese
  • Add a Translation
Please use the report function for reporting posts. All other inquiries contact: admin@fireden.net