pysc2-rl-mini
pysc2-rl-mini copied to clipboard
StarCraft II Reinforcement Learning with Pytorch - Mini Games
Results
1
pysc2-rl-mini issues
Sort by
recently updated
recently updated
newest added
In worker.py, we need to sample experience by using local model and then backpropagate the gradients of total loss. The total loss is composed of loss_of_actor, loss_of_critic and entropy. In...