hardmaru / WorldModelsExperiments

World Models Experiments

hardmaru/WorldModelsExperiments Issues

Why I can't use only 1 worker while training the controller
Closed 4 years ago
python train.py gives a CalledProcessError
Closed 6 years ago12
Is antithetic sampling doing anything for CMA-ES?
Updated 4 years ago
tf_vae.json empty after running vae_train.py
Updated 4 years ago4
render_mode=False is useless. Fake option not to render
Updated 4 years ago4
Ask for advice
Closed 5 years ago1
full episodes in extracting date
Updated 5 years ago1
'CarRacingWrapper' object has no attribute '_render'
Closed 6 years ago3
Gray screen on running dream_model.py
Closed 5 years ago3
About the new version
Closed 5 years ago1
question about temperature adjustment in MDN-RNN
Closed 5 years ago
t1
Closed 5 years ago
t1
Closed 5 years ago
Sketchy logic in vae_train.py:create_dataset
Updated 5 years ago1
MemoryError in vae_train.py
Updated 5 years ago5
MemoryError on doomrnn
Updated 5 years ago3
Out of memory when running extract.bash due to multiple extract.py using DoomTakeCoverWrapper
Updated 5 years ago1
Can not install doom-py, is thers something to be done except the install instructions?
Updated 5 years ago8
cannot reshape array of size 51529 into shape (227,227,3)
Closed 5 years ago2
Memory leak and potential fix
Closed 5 years ago1
the training of CMA-ES shows high average reward but when you just check the model against the log the rewards are practically zero
Closed 5 years ago3
Porting to other gym environments
Closed 6 years ago2
Question about the VAE's KL-loss
Closed 6 years ago1
MDN RNN Loss
Closed 6 years ago13
Questions about the doom's action space
Closed 6 years ago2
Takes more than 12 hours for training VAE Model
Closed 6 years ago11
Train RNN loss goes to NaN
Closed 6 years ago6
ImportError: No module named 'doom_py'
Closed 6 years ago1
ValueError: cannot reshape array of size 27648 into shape (1,64,64,3)
Closed 6 years ago7