Zjowowen's workspace
Runs
7
State
Notes
User
Tags
Created
Runtime
Sweep
adv_abs_max
cur_lr
entropy_loss
env step
episode return mean
grad_norm
policy_loss
total_loss
train iter
value_loss
Finished
-
zjowowen
1h 38m 44s
-
2.77587
0.0003
0.45298
9994345
240.8737
427.48398
0.15129
12.74014
31001
25.17861
Finished
-
zjowowen
2h 20m 21s
-
3.54116
0.0003
0.00021877
19881738
-697.40601
2488.47803
0.000010077
315.23038
62001
630.46075
Failed
-
zjowowen
2h 21m 9s
-
4.77606
0.0003
3.4979e-21
19880589
-671.51013
1127.8324
0
35.8421
62001
71.6842
Failed
-
zjowowen
1h 13m 4s
-
4.70826
0.0003
0.28003
9934033
250.44917
1077.96851
0.0097783
114.13655
31001
228.2541
Finished
-
zjowowen
26m 37s
-
3.64294
0.0003
0.53053
3843566
-90.73119
1003.12671
-0.0060863
72.17348
12001
144.36021
Crashed
-
zjowowen
1m 31s
-
2.35923
0.0003
1.17526
320
-1367.59534
3427.5752
0.10358
1153.31628
1
2306.42773
Failed
-
zjowowen
34m 9s
-
5.43444
0.0003
0.6816
3858190
166.28937
68.25612
0.061864
0.95538
12001
1.78839
1-7
of 7