wassname/DeepRL
1
0 Fork 0
mirror of https://github.com/wassname/DeepRL.git synced 2026-10-29 12:40:58 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update DDPG

Browse Source
This commit is contained in:
Shangtong Zhang committed 2018-01-19 11:24:32 -07:00
1 parent db49a76c53
commit eb16eeb2a1
3 files changed
+20 -29
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

agent/DDPG_agent.py
+1 -1
View File
@@ -97,7 +97,7 @@ class DDPGAgent:
actions = actor.predict(states, False)
var_actions = Variable(actions.data, requires_grad=True)
q = critic.predict(states, var_actions)
q.backward(torch.ones(q.size()))
q.backward(critic.FloatTensor(np.ones(q.size())))
actor.zero_grad()
self.actor_opt.zero_grad()