search

datamllab / rlcard

Reinforcement Learning / AI Bots in Card (Poker) Games - Blackjack, Leduc, Texas, DouDizhu, Mahjong, UNO.
http://www.rlcard.org
MIT License
2.78k stars 615 forks source link

calc reward? #301

Open Walhalla-Summary opened 10 months ago

Walhalla-Summary commented 10 months ago

Why is the training reward always negative? @zhengsx

Walhalla-Summary commented 10 months ago

@kaiks

daochenzha commented 10 months ago

@Walhalla-Summary It depends on which game environment you are using