Performance of RND at Montezuma's Revenge

simoninithomas / Deep_reinforcement_learning_Course

Implementations from the free course Deep Reinforcement Learning with Tensorflow and PyTorch

http://www.simoninithomas.com/deep-rl-course

3.74k stars 1.23k forks source link

Closed kimbring2 closed 4 years ago

kimbring2 commented 4 years ago

Hi, Thank you for sharing nice code.

I am training Random Network Distillation code for playing Montezuma's Revenge.

Screenshot from 2020-06-22 14-31-12

My total reward seems to have stopped at around 3900 for more than a day. If I wait more, are there some chance score may rise up?

I need some advice from you!!

Sincerely, From Dohyeong