Deep RL Bootcamp TAs Research Overview

 

 

 

model free: high variance. model based: high bias

 

 

 

 

 

 

 

 

 

 

 

 

within 1h of human demonstration of each task, 

VR!!!

 

 

 

原文地址:https://www.cnblogs.com/ecoflex/p/8990885.html