RoboFQE: Rollout-Free Evaluation of Visual Robot Policies from Offline Trajectories

2026-11-09来源 arXiv cs.ROEnglish
arXiv:2610.18699v2 Announce Type: replace Abstract: Evaluating robot policies before deployment typically requires producing new trajectories through real-world execution, simulators, or learned world models. These rollout-based approaches impose infrastructure requirements; simulator and world-model evaluators additionally face prediction errors that can compound over the evaluation horizon. In this paper, we study off-policy evaluation as an alternative to rollout-based robot-policy evaluation methods. Specifically, we introduce RoboFQE, an evaluator that estimates the discounted expected return of a target policy from offline robot trajectories without estimating a behavior-policy density, combining fitted Q-evaluation with a pretrained vision foundation model and learned terminal success annotation to bridge the gap between standard OPE benchmarks and continuous-control visual manipulation. Controlled experiments across simulated and real-world manipulation tasks show that RoboFQE produces accurate discounted-return estimates and preserves policy rankings even on long-horizon manipulation tasks where video world-model evaluators are degraded by autoregressive prediction errors. Ablation experiments show that pretrained vision encoders substantially outperform from-scratch alternatives, particularly on long-horizon tasks, and that learned terminal success annotation enables evaluation without ground-truth reward labels with only slight reduction of accuracy.

原文:https://www.a8q9.cn/en/article/robofqe-rollout-free-evaluation-of-visual-robot-policies-from-offline-trajectori-15e499.html

相关文章