Closed LinZichuan closed 7 years ago
In gym, terminal is True only when lives is 0. But in act() function of GymEnvironment class, it seems that terminal is True when live decrease. It will influence num_game and episode reward.
DeepMind does that when they publishing their Nature paper.
In gym, terminal is True only when lives is 0. But in act() function of GymEnvironment class, it seems that terminal is True when live decrease. It will influence num_game and episode reward.