DQN-using-PyTorch-and-ML-Agents
DQN-using-PyTorch-and-ML-Agents copied to clipboard
bool "train_mode" in banana env
Hi, love your implementation, however, i am curious what the variable "train_mode" in env.reset() does? Can you shortly explain what the difference between "train" and "test" mode is regarding the returned state-values? Thank you in advance!