Rhythm Garg
@rhythmrg
One of the most interesting unsolved problems in RL is how to train directly on production traces.
We know how to do this reasonably well when the feedback is instructive or prescriptive: distill from a strong teacher that can look at the trace and tell the model what it should
We know how to do this reasonably well when the feedback is instructive or prescriptive: distill from a strong teacher that can look at the trace and tell the model what it should
20 510