search

DeepX-inc / machina

Control section: Deep Reinforcement Learning framework
MIT License
278 stars 45 forks source link

fix mean of loss with rnn option #198

Closed rarilurelo closed 5 years ago

rarilurelo commented 5 years ago

torch.mean(loss * out_masks) should be replaced by torch.sum(loss * out_masks) / torch.sum(out_masks)