WorldModelsExperiments
WorldModelsExperiments copied to clipboard
World Models Experiments
To me it looks like we are just re-using the same seed twice which would waste compute and effectively cut our population size in half(seen here in [train.py](https://github.com/hardmaru/WorldModelsExperiments/blob/244f79c2aaddd6ef994d155cd36b34b6d907dcfe/carracing/train.py#L304))? It seems...
Greetings, I am trying to reproduce the experiment on a DGX station I currently have access to, and the fist two steps looks alright, but the result of the command:...
render_mode = False means there is 'rgb_array' instead of 'human'. Somehow it still renders.
What's the reasoning behind using full 1000-frame episodes even when the game fails before 1000 steps? It seems to result in a lot of useless images (the ones after failure)...
I'd submit a pull request, but the logic is likely going to get heavily overwritten by a memory-efficient loader, so I'll post this here and we'll see what happens. As...
Running `python vae_train.py` prompts a memory error on my system. I felt bad about this, but after running the numbers, vae_train.py needs to allocate ~125 GB of memory to this...
I am encountering what appears to be an error where the program is using too much memory: When I load 500 episodes, the program runs fine and VAE gets trained...
I am able to run a single instance of extract.py. But when i run extract.bash, it causes an out of memory error. > 2019-01-17 03:20:10.196729: E tensorflow/stream_executor/cuda/cuda_driver.cc:936] failed to allocate...
I tried several times to install doom-py, including 'pip3 install doom-py', install from the source code, 'pip3 install ppaquette-gym-doom', it always failled. Is there something else I can do?