MountainCar_DQN_RND icon indicating copy to clipboard operation
MountainCar_DQN_RND copied to clipboard

Playing Mountain-Car without reward engineering, by combining DQN and Random Network Distillation (RND)

Results 3 MountainCar_DQN_RND issues
Sort by recently updated
recently updated
newest added

I think that the value RND return as the intrinsic reward is not good in DQN. And I think it can be used to select action. So the dimension of...

![combined_return_plot](https://user-images.githubusercontent.com/46422351/50738963-fe1ae500-11e1-11e9-9cf1-084f067ef79f.png)

![real_return_plot](https://user-images.githubusercontent.com/46422351/50738799-a29c2780-11e0-11e9-82f4-e1ac46ee1a3e.png)