search

carpedm20 / deep-rl-tensorflow

TensorFlow implementation of Deep Reinforcement Learning papers
MIT License
1.6k stars 396 forks source link

is_training set to false for play #14

Closed dillonalaird closed 7 years ago

dillonalaird commented 7 years ago

is_training should be set to False when in play so score is cumulated over multiple lives.