X4Val learns transferable neural predictors from non-paired multi-domain data and incorporates them into control-variates estimators to reduce variance in real-world robotic policy evaluation by up to 38.4%.
ArXivabs/2402.04580(2024)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Recasts sampling-based nonconvex optimization as smoothed gradient descent to obtain non-asymptotic convergence guarantees and introduces the DIDA annealed algorithm that converges to the global optimum.
citing papers explorer
-
X4Val: Learning Neural Surrogates for Variance-Reduced Policy Evaluation
X4Val learns transferable neural predictors from non-paired multi-domain data and incorporates them into control-variates estimators to reduce variance in real-world robotic policy evaluation by up to 38.4%.
-
Global Convergence of Sampling-Based Nonconvex Optimization through Diffusion-Style Smoothing
Recasts sampling-based nonconvex optimization as smoothed gradient descent to obtain non-asymptotic convergence guarantees and introduces the DIDA annealed algorithm that converges to the global optimum.