What am I doing wrong? - Githubissues

keon / deep-q-learning

Minimal Deep Q Learning (DQN & DDQN) implementations in Keras

https://keon.io/deep-q-learning

MIT License

1.29k stars 455 forks source link

What am I doing wrong? #11

Closed mvrozanti closed 6 years ago

mvrozanti commented 7 years ago

I'm trying to test this out using a minor TicTacToe game but I'm failing miserably for days. DQN keeps choosing negative rewards.

haoran-zhang commented 6 years ago

You can see the new issue I posted, there is a bug in this implementation. I also failed at my first try on Lunar-Lander game. Btw, the repo is already cold maybe ...

keon commented 6 years ago

I fixed it. sorry guys for taking too long