Ben Lau
Ben Lau
@nsidn98 cool it works! Thanks
Hi, are you using Keras default weight initialization? Would you try to initialize the weight : say a gaussian distribution with small sigma value like 0.001 or 0.01? On Thu,...
See the API reference below : https://keras.io/initializers/ On Sun, Apr 9, 2017 at 12:03 PM, AmirCognitive wrote: > I am not familiar with your Keras version, can you say which...
Can you explain a bit more what does it mean by "awkward post"? Do you have any screen capture? I never experience this problem (Other people also manage to install...
Can you uncomment lines 146 to 155 in gym_torcs.py during training ? I uncomment it during actual testing to prove that the agent did not terminated early during actual test...
For simple track you should able to get some reasonable results within 200 episode_count. Cheers.
The line 146 to 155 in gym_torcs serve 2 purpose 1) The game will reset if the car is outside of the track 2) The game will reset if the...
Each step are like several milliseconds, for me, the agent can learn pretty decent skill like 6 to 7 hours of training. Meet001 於 2019年11月12日週二 下午2:16寫道： > Hey! > Can...
It happens at the beginning. But the agent should learn that keep hitting the side has bad reward and eventually it will drive straight. If the course is too difficult...
No. It probably means you are overfit the model in CG Speedway. I suggest you try following 1) Train on a more difficult track and test out in CG speedway...