2 comments

  • agnosticmantis 39 minutes ago
    Thanks for putting this together. Very nicely demystifies the weight-space programming phenomenon which I otherwise found quite magical and mysterious.

    It's not that the models magically "intuit" meaning from a blob of weights, but they methodically iterate on setting the weights with reasoning similar to a human engineer's reasoning.

  • robrenaud 3 hours ago
    Would PPO learn quickly from the hand engineered solution? Is PPO getting a terrible init?

    It's interesting to see how tolerant of tedium the models are.