# PrefO2O: Zero-Shot Preference Reinforcement Learning via Offline-to-Online Latent Preference Transfer

- Source: arXiv cs.RO
- Published: 2026-10-26T04:00:00.000Z
- RoboHot: https://robohot.news/en/items/de00xye8tkozblzuvxw64xfty
- Original: https://arxiv.org/abs/2610.31812

## Summary

PrefO2O proposes an offline-to-online latent preference transfer framework that enables zero-shot preference-based reinforcement learning (PbRL) on target tasks without any human feedback. The method learns a task-invariant latent preference space from a small amount of offline preference data on source tasks, disentangles transferable preference structures from task-specific variations, and uses confidence-weighted optimal transport alignment to generate pseudo-preference supervision for online reward adaptation.