wassname/pytorch-soft-actor-critic
1
0
Fork 0
mirror of https://github.com/wassname/pytorch-soft-actor-critic.git synced 2026-06-27 18:43:57 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update sac.py

Browse Source
This commit is contained in:
Pranjal Tandon
2020-02-03 14:16:34 +05:30
committed by GitHub
parent f1294bb974
commit 1b0087277d
1 changed files with 0 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
sac.py
-1
View File
@@ -64,7 +64,6 @@ class SAC(object):
qf1_next_target, qf2_next_target = self.critic_target(next_state_batch, next_state_action)
min_qf_next_target = torch.min(qf1_next_target, qf2_next_target) - self.alpha * next_state_log_pi
next_q_value = reward_batch + mask_batch * self.gamma * (min_qf_next_target)
qf1, qf2 = self.critic(state_batch, action_batch) # Two Q-functions to mitigate positive bias in the policy improvement step
qf1_loss = F.mse_loss(qf1, next_q_value) # JQ = 𝔼(st,at)~D[0.5(Q1(st,at) - r(st,at) - γ(𝔼st+1~p[V(st+1)]))^2]
qf2_loss = F.mse_loss(qf2, next_q_value) # JQ = 𝔼(st,at)~D[0.5(Q1(st,at) - r(st,at) - γ(𝔼st+1~p[V(st+1)]))^2]