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

    γ₀ is out, aiming for one policy across many robot designs

    A post invites contributions of robot platforms or URDF files to its growing morphology collection by October 15, 2026.

    CP
    KD
    JP
    5 Sources, ,

    TLDR

    A post celebrates γ₀’s release and describes its goal: training a single policy across many robot forms while varying their geometry, dynamics and actuation properties. It says the morphology collection is still growing and invites contributions by October 15, 2026.

    Combined views

    8.2K

    5 Sources, first seen 10h ago

    likes

    Combined views

    8.2K

    5 Sources, first seen 10h ago

    91 likes
    10h ago
    first seen 10h ago
    91
    4 comments
    23 saves
    12 reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    Featured Source
    4 comments
    23 saves
    12 reposts

    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

    5 Sources

    @NicoBohlingerThanks to my co-lead @BoAi0110! Thanks to everyone already helping with compute and deployment: Dichen Li, @tongzhou_mu, @SophieLueth, Nicolas Hahn, John Tucker and @breadli428! And thanks to all involved PIs: @Jan_R_Peters, @chelseabfinn, @haosu_twitr, @hiskov, @GeorgiaChal, Marc Schwager and Marco Hutter!
    @GeorgiaChalReally cool to see γ₀ out! The idea is to train a single policy across a very large space of robot morphologies, randomizing not only geometry but also dynamics and actuation properties across many different embodiments. The morphology collection is still growing, so if you have an interesting robot platform / URDF, please contribute till Oct. 15. 🤖 Congrats on this massive effort Nico!
    @Jan_R_PetersRT @NicoBohlinger: Thanks to my co-lead @BoAi0110! Thanks to everyone already helping with compute and deployment: Dichen Li, @tongzhou_mu…
    @chris_j_paxtonYeah this is how robots are going to have to work in the future
    @CSProfKGDRT @GeorgiaChal: Really cool to see γ₀ out! The idea is to train a single policy across a very large space of robot morphologies, randomiz…

    5 Sources

    @NicoBohlingerThanks to my co-lead @BoAi0110! Thanks to everyone already helping with compute and deployment: Dichen Li, @tongzhou_mu, @SophieLueth, Nicolas Hahn, John Tucker and @breadli428! And thanks to all involved PIs: @Jan_R_Peters, @chelseabfinn, @haosu_twitr, @hiskov, @GeorgiaChal, Marc Schwager and Marco Hutter!
    @GeorgiaChalReally cool to see γ₀ out! The idea is to train a single policy across a very large space of robot morphologies, randomizing not only geometry but also dynamics and actuation properties across many different embodiments. The morphology collection is still growing, so if you have an interesting robot platform / URDF, please contribute till Oct. 15. 🤖 Congrats on this massive effort Nico!
    @Jan_R_PetersRT @NicoBohlinger: Thanks to my co-lead @BoAi0110! Thanks to everyone already helping with compute and deployment: Dichen Li, @tongzhou_mu…
    @chris_j_paxtonYeah this is how robots are going to have to work in the future
    @CSProfKGDRT @GeorgiaChal: Really cool to see γ₀ out! The idea is to train a single policy across a very large space of robot morphologies, randomiz…