Predict the action for new environment - Inference

keon / deep-q-learning

Minimal Deep Q Learning (DQN & DDQN) implementations in Keras

https://keon.io/deep-q-learning

MIT License

1.29k stars 455 forks source link

Open kk2491 opened 5 years ago

kk2491 commented 5 years ago

Hi,

Thanks for the excellent repository. Extremely useful.

I have trained a model and saved the weight file in .h5 format. How would I predict the action for the new environment?

Thank you, KK

WorksWellWithOthers commented 3 years ago

You would use the action associated with the most reward that is returned when you feed the state into the model.