vietnh1009 / Super-mario-bros-PPO-pytorch

Proximal Policy Optimization (PPO) algorithm for Super Mario Bros
MIT License
1.09k stars 206 forks source link

18 stages completed with A3C #2

Closed davincibj closed 3 years ago

davincibj commented 4 years ago

In fact, I used your code completed 18/32 stages with A3C, but anyway, 29/32 is much better. Here is my A3C models you can test: 链接: https://pan.baidu.com/s/1F24higD2uXHn7TeMGRwbjw 密码: mgt3

Done world and stages

1-1,4

2-1,2,3,4

3-1,2,3,4

4-1

5-1

6-1,3

7-1,3

8-2,3

vietnh1009 commented 4 years ago

Thank you for updating me :)

vietnh1009 commented 4 years ago

@davincibj Could you send me the trained models directly to my email (nhviet1009@gmail.com), or upload them to google driver then send me the link? I cant down load from the above link. Thank you in advance

davincibj commented 4 years ago

done, pls check your gmail.

vietnh1009 commented 4 years ago

thank you so much. I got it. I will update readme soon and mention your finding :)

vietnh1009 commented 3 years ago

@davincibj Hi, Could you please re-upload the trained models to driver or something like that then resend me the link? The link you sent before, it is not valid anymore. Thank you so much

davincibj commented 3 years ago

hi, sent your gmail, 30 days left to download.

vietnh1009 commented 3 years ago

Hi, thanks so much. I will update readme and mention your finding :100: