search

tensorlayer / TensorLayer

Deep Learning and Reinforcement Learning Library for Scientists and Engineers
http://tensorlayerx.com
Other
7.34k stars 1.61k forks source link

Questions about PPO #1152

Open imitatorgkw opened 2 years ago

imitatorgkw commented 2 years ago

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？

fishzzzwl commented 2 years ago

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?