Update README

This commit is contained in:
Shangtong Zhang committed 2018-01-31 20:21:38 -07:00
1 parent 797f80d5ff
commit 3dcda7b5d5
3 files changed
+5 -5

No files matched your search

+1 -1
View File
@@ -100,7 +100,7 @@ class A2CAgent:
value_loss = 0.5 * (Variable(returns) - value).pow(2)
self.optimizer.zero_grad()
(policy_loss + value_loss).mean().backward()
(policy_loss + value_loss).sum().backward()
nn.utils.clip_grad_norm(self.network.parameters(), config.gradient_clip)
self.optimizer.step()