udacity / deep-reinforcement-learning

Repo for the Deep Reinforcement Learning Nanodegree program
https://www.udacity.com/course/deep-reinforcement-learning-nanodegree--nd893
MIT License
4.88k stars 2.34k forks source link

Fix the update formula of the OUNoise #12

Closed andremald closed 2 years ago

andremald commented 5 years ago

According to the used formula, the random values should be generated from N(0,1).

ronny-udacity commented 2 years ago

duplicate #19