Zjowowen's workspace
Runs
3
State
Notes
User
Tags
Created
Runtime
Sweep
adv_abs_max
approx_kl
clipfrac
cur_lr
entropy_loss
env step
episode return mean
episode return std
policy_loss
total_loss
train iter
value_loss
Finished
-
zjowowen
29m 53s
-
4.52055
0.013053
0.17188
0.001
0.71144
1030390
243.57916
21.98589
0.01151
20.23547
32004
40.46214
Failed
-
zjowowen
26m 24s
-
5.15666
0.015472
0.35156
0.001
0.80899
935351
246.22537
18.71206
-0.013828
38.32678
29004
76.6974
Crashed
-
zjowowen
1m 50s
-
4.10973
0.024929
0.26563
0.001
1.23246
65006
-2947.38989
3710.55151
-0.0028501
557.72395
2004
1115.47824
1-3
of 3