Questions about PPO

Open imitatorgkw opened this issue 4 years ago • 1 comments

I use PPO to make the car automatically find the way and avoid obstacles，but it didn't perform well. Similar examples use dqn network. Why can dqn but PPO not？

Jan 15 '22 00:01 imitatorgkw

I have the same question. The basic PPO (tutorial_PPO) can only arrive the goal when there are no obstacles. Moreover, why is variable "logstd" in line 91 of tutorial_PPO always zero when running?

Nov 03 '22 10:11 fishzzzwl