bacow/easy-rl
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

update

Browse Source
This commit is contained in:
JohnJim0816
2020-12-22 16:20:40 +08:00
parent 8b2e54ef85
commit b01ccd4d83
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
codes/DoubleDQN/agent.py
View File

@@ -5,7 +5,7 @@
@Email: johnjim0816@gmail.com @Email: johnjim0816@gmail.com
@Date: 2020-06-12 00:50:49 @Date: 2020-06-12 00:50:49
@LastEditor: John @LastEditor: John
LastEditTime: 2020-12-22 14:44:46 LastEditTime: 2020-12-22 16:20:35
@Discription: @Discription:
@Environment: python 3.7.7 @Environment: python 3.7.7
''' '''
@@ -101,7 +101,7 @@ class DQN:
# 计算当前(s_t,a)对应的Q(s_t, a) # 计算当前(s_t,a)对应的Q(s_t, a)
q_values = self.policy_net(state_batch) q_values = self.policy_net(state_batch)
next_q_values = self.policy_net(state_batch) next_q_values = self.policy_net(next_state_batch)
# 代入当前选择的action，得到Q(s_t|a=a_t) # 代入当前选择的action，得到Q(s_t|a=a_t)
q_value = q_values.gather(dim=1, index=action_batch) q_value = q_values.gather(dim=1, index=action_batch)
'''以下是Nature DQN的q_target计算方式 '''以下是Nature DQN的q_target计算方式