Published On Sep 25, 2018
Selfish A3C agents consume all apples in this tragedy-of-the-commons game, so they are quickly exhausted. This represents the best random seed over an extensive hyperparameter search.
show more
Selfish A3C agents consume all apples in this tragedy-of-the-commons game, so they are quickly exhausted. This represents the best random seed over an extensive hyperparameter search.