TOPReward extracts dense task-progress rewards from pretrained video-language model token probabilities without task-specific reward training. It supports success detection and reward-weighted imitation learning across real robot manipulation tasks.

Overview

Model type
Reward & evaluation
Listed versions
LeRobot TOPReward
Related robots
2

Model history

February 2026

TOPReward original method paper published

New resourcesOfficial announcement

The original paper introduces training-free token-probability rewards for robot trajectory evaluation.

This announcement

The original paper introduces training-free token-probability rewards for robot trajectory evaluation.

First arXiv disclosure of the original method, not a verified launch date of the later LeRobot implementation or a new model-weight release.

Verified November 7, 2026
View all important updates →

Papers & reports (1)

TOPReward: Token Probabilities as Hidden Zero-Shot Rewards for Robotics

Paper available

arXiv: 2602.19313DOI: 10.48550/arxiv.2602.19313
Authors & affiliations (9)

Author order: Original order

  1. Shirui ChenCorresponding author

    University of Washington · Allen Institute for AI

  2. Cole Harrison

    Amazon

  3. Ying-Chun Lee

    University of Washington

  4. Angela Jin Yang

    University of Washington

  5. Zhongzheng Ren

    University of Washington · Allen Institute for AI · University of North Carolina at Chapel Hill

  6. Lillian J. Ratliff

    University of Washington

  7. Jiafei DuanCo-advising

    University of Washington · Allen Institute for AI

  8. Dieter FoxCo-advising

    University of Washington · Allen Institute for AI

  9. Ranjay KrishnaCo-advising

    University of Washington · Allen Institute for AI

First published
2026-02-22
Latest paper revision
v2 · 2026-07-22
Venue
Not provided

Covered model versions

  • topreward · LeRobot TOPReward

    Original method paper referenced by the LeRobot implementation; not a separate evaluation of every LeRobot integration change.

Paper ↗PDF ↗

Official resources

Submit a source or correction