Added pygame as requirement and upgraded requirements;
Fixed wrong logger configuration in mountain_climb_run.py;
Fixed performance warning in mountain climbing and pole balancing config.py:
pytorch-neat/mountain_climb_run.py:32: UserWarning: Creating a tensor from a list of numpy.ndarrays is extremely slow.
Please consider converting the list to a single numpy.ndarray with numpy.array() before converting to a tensor.
(Triggered internally at ../torch/csrc/utils/tensor_new.cpp:210.)
input = torch.Tensor([observation]).to(c.MountainClimbConfig.DEVICE)
I hope this can help:
pygame
as requirement and upgraded requirements;mountain_climb_run.py
;config.py
:P.S.: Nice and clean NEAT implementation.