« first day (3711 days earlier)      last day (1592 days later) » 

chl
chl
06:27
@Glen_b Tnanks! I suppose I'm okay, for the moment at least. I hope you're going well too.
 
14 hours later…
20:11
0
Q: Problems with gradient-biased actor critic methods

user76284To my knowledge, there are at least 6 different variants of Actor Critic: \begin{array}{l l l l} \text{actor gradient} & \text{critic gradient} & \text{actor gradient biased} & \text{name} \\ \hline \sum_t \nabla_\theta \log \pi_\theta(a_t | s_t) \cdot (R_t - V_\theta) & \nabla_\theta \frac{1}{T}...

In case anyone's familiar with this area.

« first day (3711 days earlier)      last day (1592 days later) »