Zjowowen's workspace
Runs 
7
State
Notes
User
Tags
Created
Runtime
Sweep
cur_lr
env step
episode return max
episode return mean
episode return min
episode return std
q_value
target_q_value
total_loss
train iter
Finished
-
zjowowen
21h 25m 47s
-
0.0001
19995821
19
19
19
0
0.9023
0.88673
0.014636
2078010
Crashed
-
zjowowen
4h 54m 32s
-
0.0001
3561075
20
20
20
0
0.99124
0.97291
0.013775
370010
Crashed
-
zjowowen
6h 46m 33s
-
0.0001
6044686
21
21
21
0
1.05471
-
0.018351
628010
Crashed
-
zjowowen
20h 7m 8s
-
0.0001
14010217
19
19
19
0
0.98882
-
0.0060314
1456010
Finished
-
zjowowen
15h 50m 34s
-
0.0001
19995404
21
21
21
0
0.84349
-
0.012875
2077010
Finished
-
zjowowen
15m 47s
-
0.0001
434960
0
20
0
0
-1.58817
-
0.040985
45010
Failed
-
zjowowen
52m 28s
-
0.0001
1638864
0
20
0
0
0.074773
-
0.036228
170010
1-7
of 7