TAMER, the First General RLHF Algorithm from 2008, Gets New Open-Source Release

Brad Knox has released a new open-source version of TAMER, which Peter Stone notes was the first general RLHF algorithm, proposed back in 2008—over a decade before RLHF became popular.

2026-09-06 ~ 2026-09-07 · 2 related posts

• TAMER, the first general-purpose RLHF algorithm from 2008, gets a new playable version — PeterStone_TX · 2026-09-06
• TAMER, the First General-Purpose RLHF Algorithm From 2008, Gets a New Open-Source Release — dhadfieldmenell · 2026-09-07