Shaw
@shawmakesmagic
Wait so RL is just endlessly tweaking hyperparameters? I can reason out the math and theory of the system. But why 0.6 converges and 0.1 does not, baffling
6 replies
2 recasts
32 reactions
ash
@0xashes
Just like the rules of life always don't apply
0 reply
0 recast
0 reaction