Proximal-Policy-Optimization-Pytorch icon indicating copy to clipboard operation
Proximal-Policy-Optimization-Pytorch copied to clipboard

verified publisher icon Jiankai-Sun
→

Metadata

Proximal Policy Optimization(PPO) Algorithm and its distributed implementation in Pytorch

Results 1 Proximal-Policy-Optimization-Pytorch issues
Sort by recently updated
recently updated
newest added
trafficstars

PPO value function clip

Hi, why do you use maximum instead of minimum to clipping value function loss? Suppose clippinng occurs, when v_pred_old < v_clipped < v_pred < R, or reversely, the loss will...

Asuka20 avatar Asuka20

← Metadata

15
Stars
7
Forks
Watchers

Owner

verified publisher icon Jiankai-Sun

Metadata

Proximal Policy Optimization(PPO) Algorithm and its distributed implementation in Pytorch

Back