allenzren ace2bbdab9 add separate eval model class that also initializes the pre-trained policy for early denoising steps

2025-02-04 11:51:47 -05:00

..

dataset

v0.5 to main (#10)

2024-10-07 16:35:13 -04:00

eval

v0.7 (#26)

2024-11-20 15:56:23 -05:00

finetune

add separate eval model class that also initializes the pre-trained policy for early denoising steps

2025-02-04 11:51:47 -05:00

pretrain

use default epoch_start_ema=20 and update_ema_freq=10

2024-11-07 10:55:16 -05:00