You can deploy this model and start earning money today!

timaeus/
jaxgmg_al_g_sweep

Name: jaxgmg_al_g_sweep
Availability: InStock

Views

No views yet

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

timaeus/jaxgmg_al_g_sweep

OBSOLETE

timaeus/
jaxgmg_al_g_sweep