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

Using Keras RL in production

zolekode opened this issue · comments

commented

Please how do i use the framework at production time ?
here is how i defined my agent at training time:
policy = MaxBoltzmannQPolicy(); agent = DQNAgent(...)
Then i saved my weights at some point..

How do i use the agent during production ?

  • Note I don't want to train the agent at production time. I just need the predicted actions.
  • I need it to run fast. So loading the weights every time would be sub optimal.
  • The agent would be used concurrently. Would there be any concurrency problems ?

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.