search

LuEE-C / PPO-Keras

My implementation of the Proximal Policy Optisation algorithm using Keras as a backend
88 stars 24 forks source link

Dimension error？ #14

Open zt0716 opened 1 year ago

zt0716 commented 1 year ago

When using the get_action function, when p = self.actor.predict([self.observation.reshape(1, NUM_STATE), DUMMY_VALUE, DUMMY_ACTION]), observation is displayed as a tuple without the reshape attribute