wassname/DeepRL
1
0
Fork 0
mirror of https://github.com/wassname/DeepRL.git synced 2026-09-09 11:13:47 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fix a bug

Browse Source
This commit is contained in:
Shangtong Zhang
2017-11-05 18:58:14 -07:00
parent 34c6ca7dd8
commit 347d0d22cb
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
async_worker/actor_critic.py
+1 -1
View File
@@ -55,7 +55,7 @@ class AdvantageActorCritic:
if i == len(pending) - 1:
delta = reward + config.discount * R - value.data
else:
delta = reward + pending[i + 1][2].data - value.data
delta = reward + config.discount * pending[i + 1][2].data - value.data
GAE = config.discount * config.gae_tau * GAE + delta
loss += -log_prob.gather(1, Variable(torch.LongTensor([[action]]))) * Variable(GAE)
loss += config.entropy_weight * torch.sum(torch.mul(prob, log_prob))