spinning-up-a-Pong-AI-with-deep-RL icon indicating copy to clipboard operation
spinning-up-a-Pong-AI-with-deep-RL copied to clipboard

Published 20 hours ago • verified publisher icon mtrazzi
→

Metadata

Code for "Spinning Up a Pong AI With Deep RL" on FloydHub.

Results 2 spinning-up-a-Pong-AI-with-deep-RL issues
Sort by recently updated
recently updated
newest added

Training but not seeing results

I trained your network (without logging) during 12000 iterations and I'm not seeing good results. The IA is definitely improving but its nowhere to close to beat the CPU consistently....

laraconda avatar laraconda

y_train understanding

Hi, I am understanding policy gradient and trying to figure out why you didn't made use of log action probability and advantage function in calculating y_train?

parikshitag avatar parikshitag

← Metadata

54
Stars
14
Forks
Watchers

Owner

verified publisher icon mtrazzi

Metadata

Code for "Spinning Up a Pong AI With Deep RL" on FloydHub.

Back