Skip to content

exp: E29 - the logprob clamp is not why fpo-policy stands still under DPPO; its narrow noise is part of it - #65

Merged
tactino merged 4 commits into
mainfrom
exp/e29-clamp-or-noise
Sep 27, 2026
Merged

exp: E29 - the logprob clamp is not why fpo-policy stands still under DPPO; its narrow noise is part of it#65
tactino merged 4 commits into
mainfrom
exp/e29-clamp-or-noise

Commits

  1. Commits on Sep 26, 2026

  2. Commits on Sep 27, 2026