0.3.9

start wiring up dense rewarding with implicit prm

0.3.7

get rid of einx for now

0.3.4

take care of variable lengthed responses for implicit PRM

0.3.3

oops

0.3.2

export

0.3.0

add what may be a tiny breakthrough, which happened earlier last mont…

0.2.4

use unit offset trick from ohad rubin and get rid of optimizer factor…

0.2.3

0.2.3

0.2.2

What's Changed

• fix ppo accelerate by @ell-hol in #62

Full Changelog: 0.2.1...0.2.2

0.2.1

fix a bug with the final norm in palm, thanks to @conceptofmind and @…