search

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

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

Do you have results? #37

Closed zamlz closed 5 years ago

zamlz commented 5 years ago

Do you have results on the performance of the RL algorithms for this environment that I can look at without having to train an agent on my own?

Kautenja commented 5 years ago

not currently. There will be some public results sooner or later, but there is a lot on my back burner at the moment and the codebase needs refactored and frozen before running expensive training processes.

zamlz commented 5 years ago

No worries! Looking forward to it whenever you're ready ;)