rl-book-challenge icon indicating copy to clipboard operation
rl-book-challenge copied to clipboard

Published 20 hours ago • verified publisher icon mtrazzi
→

Metadata

self-studying the Sutton & Barto the hard way

Results 1 rl-book-challenge issues
Sort by recently updated
recently updated
newest added

np.argmax bias

The function np.argmax, does not cut ties randomly: eg: Q = [1,0,1] np.argmax always picks the first 1. Whereas all ties while selecting should be cut randomly. This can lead...

kvkpraneeth avatar kvkpraneeth

← Metadata

184
Stars
32
Forks
Watchers

Owner

verified publisher icon mtrazzi

Metadata

self-studying the Sutton & Barto the hard way

Back