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

    RPG robot-training pipeline turns demonstrations into targeted practice

    A post introducing RPG says it reconstructs practice tasks from demos and updates a shared skill system from failures.

    Yen-Jen WangYW
    1 Source, 4h ago, first seen 4h ago

    TLDR

    A post introducing RPG describes a real-to-sim-to-real pipeline that uses demonstration videos to guide robot practice and improve skills. It reports 30/30 successes across three tasks on real robots. In simulation, it reports 95.0% success across 22 manipulation tasks after 15 rounds of self-improvement.

    Combined views

    6.3K

    1 Source, first seen 4h ago

    Combined views

    6.3K

    1 Source, first seen 4h ago

    79 likes
    79 likes
    3 comments
    42 saves
    26 reposts
    3 comments
    42 saves
    26 reposts
    Featured Source

    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

    1 Source

    Yen-Jen Wang@wangyenjenPractice makes perfect. A truly agentic robot shouldn’t just know what to do. It should also figure out how to get better. What if a robot could watch a demonstration, figure out what it needs to practice, and learn how to get better through practice? Introducing RPG: Guided Self-Improvement for Embodied Agents, a real-to-sim-to-real pipeline that turns real-world demonstrations into targeted practice. RPG reconstructs practice tasks from demonstrations, uses demo videos to guide skill improvement, and continually updates a shared skill system from failures. On real robots, RPG achieves 30/30 successes across 3 tasks. In simulation, it reaches 95.0% success across 22 manipulation tasks after 15 rounds of self-improvement. Demo → Reconstruct → Guided Practice → Self-Improve → Go Real4h