rl-inference icon indicating copy to clipboard operation
rl-inference copied to clipboard

Multiplication multiple of expl_scale

Open CarlDegio opened this issue 1 year ago • 0 comments

in planner.py:

self.measure = InformationGain(self.ensemble, scale=expl_scale)

and

expl_bonus = self.measure(delta_means, delta_vars) * self.expl_scale

In fact, multiplied twice of expl_scale

CarlDegio avatar Mar 31 '23 14:03 CarlDegio