search

yanpanlau / DDPG-Keras-Torcs

Using Keras and Deep Deterministic Policy Gradient to play TORCS
717 stars 267 forks source link

Episode error #51

Open shizhuocaoa opened 6 years ago

shizhuocaoa commented 6 years ago

torcs_erros When I tried run your file ddpg.py as your introduction, there are some problems. Just like what is showed in the picture, the Episode is zero all the time, and the car don't move at all. I just learn RL for a short time, so I don't understand why. Would you please help me? The is my we-chat number: wa7739977526. Thank you very much.

BCWang93 commented 5 years ago

HI.Do you have this problem?when I run the ddpg.py,the terminal is output like this: Timeout for client answer Timeout for client answer Timeout for client answer Timeout for client answer Timeout for client answer Timeout for client answer Timeout for client answer Timeout for client answer Timeout for client answer Timeout for client answer Timeout for client answer Timeout for client answer Timeout for client answer Do you know how to solution this problem?Thanks!

lingyunli1994 commented 5 years ago

I see that the loss in your screenshot is always 0. Have you not changed the training mode, but have been running mode?

BCWang93 commented 5 years ago

hello,Do you solved this problem?

shushu-nantong commented 5 years ago

@BCWang93 The Timeout problem can be solved by checking the "snakeoil3_gym.py" file. If the snakeoil3_gym.py can be run without timeout errors, the ddpg.py can also work.

However, anyone knows how to solve the 0 episode problem?