SabaPivot's picture
Update logbook: Repro - Success-Conditioning as Policy Improvement: The Optimization Problem Solved by Imitating Success
a7168d6 verified
|
Raw
History Blame Contribute Delete
486 Bytes
metadata
title: >-
  Repro - Success-Conditioning as Policy Improvement: The Optimization Problem
  Solved by Imitating Success
emoji: 🎯
colorFrom: yellow
colorTo: red
sdk: static
pinned: false
tags:
  - trackio
  - trackio-logbook
  - open-experiment
  - icml2026-repro
  - paper-FEmXFeqYNZ

Repro - Success-Conditioning as Policy Improvement: The Optimization Problem Solved by Imitating Success

An open experiment logbook, published with Trackio.