Target network updates / Double-Dueling-DQN.ipynb

awjuliani / DeepRL-Agents

A set of Deep Reinforcement Learning Agents implemented in Tensorflow.

MIT License

2.24k stars 826 forks source link

Target network updates / Double-Dueling-DQN.ipynb #70

Open sanderfeliz opened 6 years ago

sanderfeliz commented 6 years ago

From my understanding the target network updates are implemented wrong in the notebook Double-Dueling-DQN.ipynb. As it updates the same step as the main network (every 4th). In this simple environment no difference will be observed but I believe for the purpose of better understanding the concept it would be nice to fix that!

Michaeljurado42 commented 5 years ago

omg i thought the same thing