Where to find and how to restore dqn_speedup model?

[odats]

I want to train DQN agent and run Pong env to see how the agent plays.

After successful completion 05_new_wrappers.py I can find only event logs files: events.out.tfevents.1556915999.ip-172-31-42-166

Where to find and how to restore dqn_speedup model?

[Shmuma]

Save of the neural network is not added in this example, but fairly straightforward thing to do. To get started you can check sample from the book here:

• save code: https://github.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On/blob/master/Chapter06/02_dqn_pong.py#L153
• play code: https://github.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On/blob/master/Chapter06/03_dqn_play.py

[odats]

Thank you for the support.

On May 7, 2019, at 12:14, Max Lapan notifications@github.com wrote:

Closed #24 https://github.com/Shmuma/ptan/issues/24.

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub https://github.com/Shmuma/ptan/issues/24#event-2323546815, or mute the thread https://github.com/notifications/unsubscribe-auth/AAHGR6YRCFW3OYNKY34A3VLPUFB7NANCNFSM4HKYLXTQ.