Zaib Ali
Zaib Ali
But upx binary already placed in controls folders
custom wrapper around the environment that tracks when invalid actions are masked and modifies the information sent to the agent accordingly
Issue
(array([-0.02680779, 0.00466264, -0.02511859, -0.04842809], dtype=float32), {}) Traceback (most recent call last): File "main.py", line 31, in action, prob, val = agent.choose_action(observation) File "D:\AI\PPO\agent.py", line 41, in choose_action state = tf.convert_to_tensor([observation],dtype=tf.float32)...
lose = nan - mse = nan while training the model and not improving the values
![Screenshot (121)](https://user-images.githubusercontent.com/65595484/221416324-0f94d94c-7543-4aea-94e7-11d73e22ff01.png) Sometimes dates are not showing and counting is also wrong