search

Kautenja / playing-mario-with-deep-reinforcement-learning

An implementation of (Double/Dueling) Deep-Q Learning to play Super Mario Bros.
MIT License
69 stars 12 forks source link

DownsampleEnv metadata #21

Closed Kautenja closed 6 years ago

Kautenja commented 6 years ago

metadata for downsampling is needed for:

Kautenja commented 6 years ago

Asteroids results in severe flickering, the current frame observation technique wont work for this game

Kautenja commented 6 years ago

all downsamplers are designed, coming in a commit soon. closing issue.