Downloads · 30 days
0
jaxgmg_al_g_sweep
timaeus/jaxgmg_al_g_sweep
jaxgmg_al_g_sweep is a machine learning model from timaeus. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
An early sweep over discount factor and alpha to see changes in behaviour.
Access
Public
Updated Apr 7, 2026
Repo size
249 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.zip75.4 GB · 98%
At a glance
- Access
- Public
- Created
- Oct 13, 2025
- Updated
- Apr 7, 2026
- SHA
- b52e9327
Model card
From the Hugging Face model README
OBSOLETE
An early sweep over discount factor and alpha to see changes in behaviour.
These models were originally used for RL1, but were trained with previous action, and with the variable learning rate bug. Do not use.
Interesting models, see wandb sweep
Trained on (1-alpha) * corner + alpha * any
al_0.68_g_0.95_any
al_0.68_g_0.975_any
al_0.68_g_0.99_any
al_0.47_g_0.99_any
Trained on (1-alpha) * corner + alpha * row
al_0.68_g_0.95_row
al_0.68_g_0.975_row
al_0.68_g_0.99_row
al_0.47_g_0.95_row
al_0.47_g_0.975_row
al_0.47_g_0.99_row
al_0.33_g_0.99_row
al_0.22_g_0.95_row
al_0.22_g_0.99_row
al_0.15_g_0.99_row
al_0.05_g_0.975_row
- Created
- Oct 13, 2025
- Updated
- Apr 7, 2026