Open flyyufelix opened 7 years ago
For the video demo in the Readme for defend_the_center scenario, do you use single_agent or multi_agent? LSTM Deep Recurrent Q network is used right?
it is the single agent implementation
So it's just a Double DQN model without the use of LSTM?
For the video demo in the Readme for defend_the_center scenario, do you use single_agent or multi_agent? LSTM Deep Recurrent Q network is used right?