Skip to main content
prabhasak
Projects
masters-thesis
Run groups
Pendulum-v0
Logs
Overview
Workspace
Runs
Logs
Files
Artifacts

Prabhasak's group workspace

Timestamps visible
2020-09-30 04:41:27
Std for returns: 84.351699
2020-09-30 04:41:27
 Generated Pendulum-v0 expert with trained BC policy. Some stats:
2020-09-30 04:41:27
2020-09-30 04:41:27
75/100 successful episodes
2020-09-30 04:41:27
2020-09-30 04:41:27
Mean return:  -147.5204439020157
2020-09-30 04:41:27
Std return:  84.35169920209958
2020-09-30 04:41:27
Max return:  -4.3696794509887695
2020-09-30 04:41:27
Min return:  -367.0426940917969
2020-09-30 04:41:27
Mean episode len:  200.0
2020-09-30 04:41:27
Optimal expert found!
2020-09-30 04:41:27
2020-09-30 04:41:32
100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 10/10 [00:04<00:00,  2.04it/s]
2020-09-30 04:41:32
stochastic policy:
2020-09-30 04:41:32
Average length: 200.0
2020-09-30 04:41:32
Std length: 0.0
2020-09-30 04:41:32
Average return: -1254.5048720958646
2020-09-30 04:41:32
Std return: 276.6980057628105