Advantage-Weighted Regression (AWR)

Saw this from the online batch RL paper.

${\theta }^{\ast }=\arg {\max }_{\theta }{\mathbb{E}}_{(s,a)\sim D}\left[e^{\beta (Q(s,a)-V(s))}\log {\pi }_{\theta }(a|s)\right]$

https://arxiv.org/abs/1910.00177