Question about Defend_the_center demo result

itaicaspi / keras-dqn-doom

Keras implementation of DQN on ViZDoom environment

53 stars 18 forks source link

Open flyyufelix opened 7 years ago

flyyufelix commented 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?

itaicaspi commented 7 years ago

it is the single agent implementation

flyyufelix commented 7 years ago

So it's just a Double DQN model without the use of LSTM?