Luke Lee

icon indicating a website link https://liwyNo.github.io

icon company University of Texas at Austin icon location Austin, TX, USA

Results 2 comments of Luke Lee

if ref_model is a copy of act_model at begining in stage3 , does it mean the kl_divergence is 0?

At beginning in stage3, kl_divergence_estimate should be zero. But, after several steps, the generation of actor model might be different from reference model. Please correct me if I make any...

if ref_model is a copy of act_model at begining in stage3 , does it mean the kl_divergence is 0?

> > At beginning in stage3, kl_divergence_estimate should be zero. But, after several steps, the generation of actor model might be different from reference model. Please correct me if I...