Skip to content
Trending eventHistorical event

RACE: Calibrated Cumulative Scoring for Rollout-Free Robot Policy Checkpoint Selection

1 reports1 reporting sourcesUpdated 5 days ago

Overview

Event synthesis

This paper presents RACE, a new metric for selecting robot policy checkpoints without costly real-world trials. Unlike averaged validation loss, which can misrank checkpoints, RACE calibrates action deviations against state-conditional thresholds derived from successful trajectories. By aggregating scores via a running product, it reduces the impact of early deviations on subsequent predictions. Experiments in simulation and on real robots show that RACE outperforms baselines across various policy backbones and tasks, with rankings aligning well with deployment success.

Generated from attributed reports · Updated 5 days ago

Event evidence and corrections

0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.

No current evidence-backed claims. Missing information remains not reported.

Report timeline

Follow attributed reports and material updates.

11/5
  1. arXiv Robotics — research abstractsSignal
    RACE: Calibrated Cumulative Scoring for Rollout-Free Robot Policy Checkpoint Selection

    This paper presents RACE, a new metric for selecting robot policy checkpoints without costly real-world trials. Unlike averaged validation loss, which can misrank checkpoints, RACE calibrates action deviations against state-conditional thresholds derived from successful trajectories. By aggregating scores via a running product, it reduces the impact of early deviations on subsequent predictions. Experiments in simulation and on real robots show that RACE outperforms baselines across various policy backbones and tasks, with rankings aligning well with deployment success.

Event coverage history

Current attention 3·Peak within the comparable range 9(2026-11-05 07:00 UTC)·Change within the comparable range over 24 hours -49%

02.557.5102026-11-0507:002026-11-0522:002026-11-0613:002026-11-0704:00

The trend compares participants observed continuously; its scope may be narrower than current attention totals. Hover or click to explore hourly observations, or use the left and right arrow keys.

Timezone · UTC

Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).