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

    Wayfarer is claimed to outperform DreamerV3, Rainbow and IQN on Atari 2600 games

    The team says an action sequence Wayfarer discovered in Montezuma's Revenge worked even in rooms the agent had never seen.

    MC
    8 Sources, 4h ago, first seen 4h ago

    TLDR

    The team behind Wayfarer says its method learns action sequences from a single stream of experience and outperforms DreamerV3, Rainbow and IQN on a challenging set of Atari 2600 games. In Montezuma's Revenge, they say those sequences let the agent reach the third screen in two orders of magnitude fewer decisions. They also report that one sequence worked in previously unseen rooms.

    Combined views

    5.1K

    8 Sources, first seen 4h ago

    Combined views

    5.1K

    8 Sources, first seen 4h ago

    114 likes
    114 likes
    9 comments
    62 saves
    23 reposts
    Featured Source
    9 comments
    62 saves
    23 reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    Today's Rank

    —

    Not ranked yet

    Today's Rank

    —

    Not ranked yet

    8 Sources

    @MarlosCMachadoI'm excited to share Erik's work! Mastering Atari 2600 Games with Discovered Options We have a general-purpose option-discovery method that works w/ high-dimensional observations, tabula rasa, using a single stream of experience! It outperforms DreamerV3, Rainbow, and IQN! 1/94h

    8 Sources

    @MarlosCMachadoI'm excited to share Erik's work! Mastering Atari 2600 Games with Discovered Options We have a general-purpose option-discovery method that works w/ high-dimensional observations, tabula rasa, using a single stream of experience! It outperforms DreamerV3, Rainbow, and IQN! 1/94h