3 Commits

Author	SHA1	Message	Date
Dobromir Popov	b80e1c1eba	better rewards, fixed TZ at last	2025-08-08 01:53:17 +03:00
Dobromir Popov	902593b5f3	new training process and changes to the models (wip)	2025-04-01 18:43:26 +03:00
Dobromir Popov	4eac14022c	RL training	2025-03-31 03:31:54 +03:00