Closed qipengliuNTU closed 4 years ago
Hello,
If you train from pixels, you should set N_COMMAND_HISTORY
to zero.
See warning here: https://github.com/araffin/learning-to-drive-in-5-minutes/blob/master/donkey_gym/envs/vae_env.py#L92
Oh~ I didn't find this warning message. Now I can train the car from pixels. Thanks very much for your help!!! I am closing this issue.
@qipengliuNTU Hello Did you manage to train the model with the image input?
I set the N_COMMAND_HISTORY to zero but I encountered the following issue.
ValueError: could not broadcast input array from shape (38400) into shape (80,160,3)
@qipengliuNTU @araffin I tried to edit postprocessing_step
and reset
in vae_env.py so that it only return observation.flatten() when using VAE training. The code can run but seem have some issue on the training. The model seem didn't learn and keep go off the track when it start a new episode....
From my understanding, if I don't set the arguments 'vae_path' and 'random_features', the car will learn from pixels, as mentioned in 'train.py':
However, when I run the following command,
python train.py --algo sac -n 5000 --teleop
some error message comes up:Any advice on this problem? Thanks very much.