Zjowowen's workspace
Runs
2
State
Notes
User
Tags
Created
Runtime
Sweep
action
actor_loss
critic_loss
cur_lr_actor
cur_lr_critic
env step
episode return max
episode return mean
episode return min
episode return std
q_value
td_error
total_loss
train iter
Finished
-
zjowowen
1m 33s
-
-0.098125
36.73239
0.90931
0.001
0.001
77600
-0.9192
-242.15039
-418.81583
158.03273
-37.35729
0.90931
37.6417
3202
Crashed
-
zjowowen
12m 24s
-
0.0066927
183.27608
13.60765
0.001
0.001
147200
429.4231
-1289.59705
429.4231
429.4231
-183.372
13.60765
196.88373
6102
1-2
of 2