Kyle Tse

any news on this?

> K.function() with output = [] yeild error given the newer version of Keras. > Down-grade it to 2.1.6 like suggested in the README. I have the same issue. Besides...

I still don't understand what is the adv of normalizing the advantages.

I have the same question too. Searched for an answer but no luck. Please tell me the reason why it uses maximum instead of minimum.

Ok. I got the answer now. Because baseline calculate pgloss1 and pgloss2 with negative sign. So that it uses maximum afterward.

I have the same question and even don't understand why we need to do clipping on value loss.

also why we need to clip it using the same value as the one that policy loss ratio using?

I am looking forward to your A3c too.

@vlasky I am working to support mysql2. as I don't want my project to install both two mysql and mysql2 packages. Also, ZongJi use single connection for both connection and...

 https://realfavicongenerator.net/favicon_checker#.YwDplS7P0Q8  but every others are fine. just these two places confusing me a lot.