Dobromir Popov b3c5076e37 training: conviction-aware reward shaping

2025-08-10 13:23:29 +03:00

..

dev_notes.md

training: conviction-aware reward shaping

2025-08-10 13:23:29 +03:00

problems.md

integrating new CNN model

2025-07-23 16:59:35 +03:00