Zjowowen's workspace
Runs
3
State
Notes
User
Tags
Created
Runtime
Sweep
alpha
critic_loss
cur_lr_p
cur_lr_q
env step
episode return max
episode return mean
episode return min
episode return std
policy_loss
target_q_value
td_error
train iter
transformed_log_prob
twin_critic_loss
Finished
-
zjowowen
3h 11m 17s
-
0.2
41.05787
0.001
0.001
608000
12113.07715
12024.45215
11788.63379
98.07223
-804.31543
804.75647
40.21881
598001
6.81722
39.37975
Finished
-
zjowowen
3h 9m 22s
-
0.2
41.05787
0.001
0.001
608000
12113.07715
12024.45215
11788.63379
98.07223
-804.31543
804.75647
40.21881
598001
6.81722
39.37975
Crashed
-
zjowowen
3h 52m 32s
-
0.2
23.15736
0.001
0.001
607000
11690.08887
11557.51563
11439.00879
85.78584
-827.9798
828.07629
24.25017
597001
7.11038
25.34297
1-3
of 3