• Home
  • Technology
  • Gaming
  • Entertainment
  • World & Business
  • Science
  • Sports
  • AI
HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
  • HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
    • Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI
    AI

    NetHack play reportedly reaches a 19.5k score using random classes

    The user also highlights regularly reaching The Castle and wants to see the result translated into BALROG's progress metric.

    TR
    JS
    2 Sources, 16d ago, first seen 16d ago

    TLDR

    A user praises a reported 19.5k NetHack score using random classes, saying play regularly reaches The Castle. They would like to see that performance expressed through BALROG's progress metric.

    Combined views

    8.4K

    2 Sources, first seen 16d ago

    55 likes

    Combined views

    8.4K

    2 Sources, first seen 16d ago

    55 likes
    Today's Rank

    —

    Not ranked yet

    Today's Rank

    —

    Not ranked yet

    5 comments
    21 saves
    4 reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    5 comments
    21 saves
    4 reposts

    2 Sources

    @_rocktCongrats on achieving 19.5k score using random classes in @NetHack_LE, getting regularly to The Castle! That's really cool. Would love to see that translated to https://balrogai.com's progress metric.
    @jsuarez@_rockt @finlay_sanders @NetHack_LE Not bad for a model <<1/1000 of the size with no human data!

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    2 Sources

    @_rocktCongrats on achieving 19.5k score using random classes in @NetHack_LE, getting regularly to The Castle! That's really cool. Would love to see that translated to https://balrogai.com's progress metric.
    @jsuarez@_rockt @finlay_sanders @NetHack_LE Not bad for a model <<1/1000 of the size with no human data!