TAMER, the First General-Purpose RLHF Algorithm From 2008, Gets a New Open-Source Release

dhadfieldmenell · x · 2026-09-07

Brad Knox has released a new open-source version of TAMER, making it easy for anyone to experiment with the algorithm. Peter Stone notes that TAMER was the first general-purpose RLHF algorithm, introduced back in 2008. Ishan Durugkar says TAMER shaped many of his PhD explorations, and the new release lets a wider audience play with this pioneering work in human-in-the-loop reinforcement learning.

Related event: TAMER, the First General RLHF Algorithm from 2008, Gets New Open-Source Release(2 posts)→

Original post →

More from Research

Research channel →