Reinforcement Learning Still A Viable Path To AGI

Поделиться
HTML-код
  • Опубликовано: 12 дек 2024

Комментарии • 6

  • @Crack-tt2dh
    @Crack-tt2dh Год назад +1

    I think curiosity is very likely to be an important factor in achieving AGI. Without a curiosity mechanism, it means the agent may never proactively engage in learning. Almost all animals in the natural world have a curiosity mechanism, and I believe this may explain some issues.

  • @predictus5228
    @predictus5228 Год назад

    Great overview Phil! And good refresh on that Sutton paper (had forgotten about that one). Chris

  • @harishs13
    @harishs13 Год назад

    Thank you so much Phil! Excellent overview.

  • @bourgeoisremi9778
    @bourgeoisremi9778 Год назад +6

    As impressive as they are, I do not believe LLM are the path to AGI. It might look like it, but I don't think it can... I'm a firm believer that RL is the way !

  • @quentinvacher7961
    @quentinvacher7961 Год назад

    Thank you :)

  • @juleswombat5309
    @juleswombat5309 Год назад +1

    Reinforcement Learning is simply too fragile, none robust route, requiring excessive reward shaping. There is no clear way towards AGI, and we are no nearer to it, than when we believed we were within decade or so in the mid 1960s (Minsky et al). Avoid the AI hype.