Feature - Train models against previous model

zapper-95 / Coup-RL

Models trained to play the card game Coup

0 stars 0 forks source link

Closed zapper-95 closed 6 months ago

zapper-95 commented 7 months ago

From #20, now would be good to train the model against the previous model instead of random or the current model being used

zapper-95 commented 6 months ago

no longer using sb3