X4Val: Learning Neural Surrogates for Variance-Reduced Policy Evaluation
2026-06-03 • Robotics
Robotics
AI summaryⓘ
The authors address the challenge of evaluating robot learning systems when real-world test data is limited and expensive. They propose X4Val, a method that uses different kinds of data—including simulations and past records—to better estimate real-world robot performance. X4Val creates a shared space to connect these data types and learns a predictor to reduce uncertainty in evaluation, even when the data aren't directly matched. They show that this approach lowers variance significantly in tests with self-driving cars and robot tasks. Overall, their work helps get more reliable performance estimates from mixed and limited data sources.
robot learning evaluationvariance reductioncontrol variatesdomain adaptationsimulation to real transferautonomous drivingrobot manipulationmulti-domain datasample efficiencypredictive modeling
Authors
Rachel Luo, Michael Watson, Apoorva Sharma, Heng Yang, Han Qi, Edward Schmerling, Sushant Veer, Boris Ivanovic, Marco Pavone
Abstract
Rigorous evaluation of learning-based robotic systems is an essential prerequisite for deployment. However, real-world test data is expensive to gather; moreover, in a typical iterative development context, data gathered from the latest policy is necessarily limited in scale. This motivates evaluation methodologies that make use of heterogeneous data sources, including simulation, historical policy logs, and data collected from related platforms or environments. While such auxiliary data are abundant and inexpensive, they are generally not directly representative of real-world outcomes -- for example, performance in simulation may differ substantially from performance in the real world -- making their principled use for high-confidence performance estimation challenging. In this paper, we introduce X4Val, a general framework for variance-reduced real-world metric estimation in the presence of non-paired, multi-domain data. X4Val embeds samples from real and auxiliary domains into a shared representation space and learns a transferable predictor of real-world metrics; this learned predictor is then incorporated into a control-variates estimator, enabling variance reduction even when paired samples are unavailable. We provide theoretical analysis and empirical evaluations on autonomous driving and real-world robot manipulation tasks, domains across which X4Val achieves up to 38.4% variance reduction and demonstrates consistent improvements over strong baselines. These results show that non-paired, heterogeneous data can be leveraged to substantially improve the sample efficiency of rigorous robotic system validation.