Not able to solve any level using provided trained models

uvipen / Super-mario-bros-PPO-pytorch

Proximal Policy Optimization (PPO) algorithm for Super Mario Bros

MIT License

1.07k stars 201 forks source link

Not able to solve any level using provided trained models #8

Closed Dhiraj100892 closed 3 years ago

Dhiraj100892 commented 4 years ago

Hi,

I have tried to use the provided models in trained_models. Using them agent was able to proceed however couldn't solve the complete level. Either it used to get stuck or die. Were you able to complete the levels using these models?

uvipen commented 4 years ago

Yes, I just checked again and all of them still work well. Could you clarify how you use these pretrained models?