@jik_wtf You're right about the things that make it the same as RL, it's just not where the boundaries of what people call RL vs other training methods are typically drawn.
in reply to: 1965675596127916061
same thread: 1965659230486364420 1965661860969193841 1965671437785850025 1965675596127916061 1965676704363618803 1965683813461491807
Reproduced against link rot, credited and linked to its original. Yours and you’d rather it weren’t here? Open an issue.