AugustoPeres

DQN ability to skip linear layer in the network

2

Hi, I am posting because I want to train a DQN-agent using a geometric deep learning model that obeys the very specific rule (equivariance): network(P_1 * State * P_2) =...

For training reasons I had to write my own sampler. Something like: ```python class MySampler(torch-utils.data.Sampler): def __init__(self, data, batches_per_epoch, batch_size): # some python code def __iter__(): # My iter method...

I have a training script using ray, pytorch lightning and mlflow. When I try to use ray lightning it seems to open another strategy: First in my script I have...

inductiva/tasks#22