search

nikhilbarhate99 / PPO-PyTorch

Minimal implementation of clipped objective Proximal Policy Optimization (PPO) in PyTorch
MIT License
1.57k stars 332 forks source link

question #63

Open yinshuangshuang621671 opened 1 year ago

yinshuangshuang621671 commented 1 year ago

May I ask a question: Why is the with torch.no_grad(): used in ppo.select_action ??