Zjowowen's workspace
Runs
6
State
Notes
User
Tags
Created
Runtime
Sweep
action
actor_loss
critic_loss
critic_twin_loss
cur_lr_actor
cur_lr_critic
env step
episode return max
episode return mean
episode return min
episode return std
q_value
q_value_twin
td_error
total_loss
train iter
Finished
-
zjowowen
3h 11m 54s
-
-0.20578
-57.15067
17.71173
16.93643
0.001
0.001
2825780
292.49594
264.28076
248.30394
16.906
56.29313
56.38549
17.32408
-22.50251
117102
Failed
-
zjowowen
1h 52m 44s
-
0.045323
-8.19378
20.5562
20.13394
0.001
0.001
1752449
-
242.06848
-
-
8.11371
8.19012
20.34507
32.49636
72702
Finished
-
zjowowen
1h 52m 47s
-
-0.051418
-31.06068
3.84208
4.0311
0.001
0.001
1946307
-
250.31107
-
-
30.76172
30.63108
3.93659
-23.1875
80702
Crashed
-
zjowowen
1h 37m 16s
-
0.0055801
-7.19802
20.22886
20.26446
0.001
0.001
1531871
-
183.68045
-
-
6.84834
6.66499
20.24666
33.29531
63502
Finished
-
zjowowen
1h 12m 53s
-
0.04705
6.21255
24.0405
23.71941
0.001
0.001
1046854
-
254.69359
-
-
-6.38177
-6.32807
23.87996
53.97246
43402
Failed
-
zjowowen
1h 18m 10s
-
0.002131
-28.00507
16.69436
16.47418
0.001
0.001
1210612
-
245.7849
-
-
27.56917
27.60698
16.58427
5.16347
50202
1-6
of 6