BipedalWalker-v3-PPO Table – Weights & Biases

Skip to main content

We are currently experiencing performance degradation across the wandb.ai service, and are currently investigating remediations

Zjowowen's workspace

Runs

1

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

5h 23m 20s

-

2.07414

-8.3994e-9

0.40502

0.62002

0.001

2.16557

4996684

212.2766

116.01504

-0.025931

779680

0.54611

7.87524

6.93219

1-1

of 1