mlpack  blog
Proximal Policy Optimization - Week 2

Proximal Policy Optimization - Week 2

Xiaohong J, 09 June 2019

This week I fixed the review comment of Prioritized Experience Replay. I have more clear understanding template programming. Sometimes, we can reuse the template parameter when the class has the similar behaviors. I have a feeling that mlpack community member is really conscientious. Even though I thought that it is ready for merging, Zoq can find many minor style problems. I really thanks zoq, manish7294 and rcurtin's review. I really learn lots of from your.

I have short trip during our traditional Chinese festival, Dragon Boat Festival. The scenery is really beautiful, I have upload some pictures and write summary for this trip (but in Chinese). Link