Reinforcement Learning library for public
Repo pythonlessons/RockRL, read from GitHub 1 d ago. pythonlessons has not joined Take My Repo.
ema_ratio parameter to rockrl.tensorflow.ppo to control the exponential moving average ratio of the old and new networksrockrl.tensorflow.ppo act function to use training mode while training and evaluation mode while evaluatingclose() method to rockrl.tensorflow.ppo to close tensorBoardLogger after trainingrockrl.tensorflow.ppo to use threading while logging, to save timerockrl.utils.VectorizedEnv to return info dictionaries in list instead of tuplestensorflow_probability dependency