Zjowowen's workspace
Runs
5
State
Notes
User
Tags
Created
Runtime
Sweep
cur_lr
entropy_loss
env step
episode return max
episode return mean
episode return min
episode return std
policy_loss
total_loss
train iter
value_loss
Finished
zjowowen
17h 1m 2s
-
0.0006
0.87124
19774973
330
330
330
0
-0.010634
0.026894
38502
0.092482
Failed
zjowowen
14h 54m 35s
-
0.0006
0.86409
19774943
425
425
425
0
-0.021542
0.022771
38502
0.10591
Failed
zjowowen
14h 40m 21s
-
0.0006
0.40999
19770678
1975
1975
1975
0
-0.007556
0.022767
38502
0.068847
Crashed
zjowowen
13h 55m 48s
-
0.0006
0
15571918
0
0
0
0
0
4.3410e-8
60502
8.6820e-8
Crashed
zjowowen
21m 59s
-
0.0006
1.68246
257840
50
50
50
0
-0.011718
-0.0081158
1002
0.040854
1-5
of 5