HalfCheetah-v3-PPO Table – Weights & Biases

Skip to main content

Zjowowen's workspace

Runs

4

adv_max

adv_mean

approx_kl

clipfrac

cur_lr

entropy_loss

env step

episode return mean

episode return std

policy_loss

train iter

value_loss

value_max

value_mean

Finished

-

zjowowen

2y ago

2h 56m 6s

-

5.82367

-2.8983e-9

0.037898

0.36628

0.0003

10.32084

4997487

5182.31152

61.89888

-0.024374

156100

8.98711

37.52298

34.26745

Finished

-

zjowowen

2y ago

1h 44m 6s

-

2.42335

-7.1526e-9

0.050013

0.42681

0.0003

10.24819

4997497

1303.10669

40.65311

-0.037948

156100

0.96972

21.40917

19.71234

Finished

-

zjowowen

2y ago

5s

-

-

-

-

-

-

-

-

-

-

-

-

-

-

-

Finished

-

zjowowen

2y ago

4s

-

-

-

-

-

-

-

-

-

-

-

-

-

-

-

1-4

of 4