agent57_pytorch

agent57_pytorch copied to clipboard

RayOutOfMemoryError: More than 95% of the memory on node xxx is used

1

Hello, thank you so much for the reproduction code! I have encountered `RayOutOfMemoryError` when running the code. To address this issue, I have tried set `num_agents` from the default of...

AptX395

cuDNN error: CUDNN_STATUS_EXECUTION_FAILED

2

I am trying to run your code on a fresh install of Ubuntu 20.04 with Python 3.9.5, and CUDA 11.6 / cuDNN 8.3.2, but when executing main.py the following cuDNN...

nhansendev

Fix the flipped order of in_rewards and ex_rewards in 3 places Fix typos

Rottenham

@help

2

Is there any model file that can be successfully reproduced? The effect of my training is not good.@ @yuta0821 @yuta0821

wangwuc

@Obliman

3

@Obliman Do you have the model file of agent57 that has been trained? The results I trained are not good. _Originally posted by @yuta0821 in https://github.com/yuta0821/agent57_pytorch/issues/1#issuecomment-1046775440_

wangwuc