Giters

keras-rl / keras-rl

Deep Reinforcement Learning for Keras.

Home Page:http://keras-rl.readthedocs.io/

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Where is the environment specified in DQNAgent

kdawar1 opened this issue · comments

commented

I am trying to understand where exactly in the DQNAgent is the environment specified. I see that there is mentions of self.step, self.recent_observation, self.recent_action, reward and terminal but I don't see where are these being generated. I am trying to develop my own environment and am trying to understand how it will pass through the system. Also, in the statement
dqn.fit(env, nb_steps=3000, visualize=False, verbose=1)
I don't understand how is the environment passed into the function.
Thank you!

commented

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.