Why are we training the neural network for only 1 epoch

keon / deep-q-learning

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

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

MIT License

1.28k stars 454 forks source link

Why are we training the neural network for only 1 epoch #31

Open daysofthunder98 opened 4 years ago

daysofthunder98 commented 4 years ago

The neural network would not converge for only 1 epoch right?

WorksWellWithOthers commented 3 years ago

The behavior we want from the Neural Network is to give us a similar output when given a similar state. As for the epoch, the model is constantly retrained after each step/episode (or however the author sets it up).