activity
20242026
collaborators

15 papers

stat.ML2026

Round-Trip Consistency: Bidirectional Diffusion Models Can Predict Their Own Rollout Errors

Alexander Scheinker

Autoregressive models accumulate error over long rollouts, yet at deployment there is no ground truth to measure it against. We train a single conditional latent diffusion model th…

stat.ML2026

Bidirectional Autoregressive Latent Diffusion for Forward and Inverse Magnetohydrodynamics

Alexander Scheinker

This work presents a new bidirectional autoregressive latent diffusion approach for predicting the evolution of multiple fields (mass density, pressure, velocity, and magnetic fiel…

cs.LG2026

Mahalanobis-Guided Latent OOD Detection for Hybrid ES-DRL Control in Time-Varying Systems

Shaifalee Saxena, Alexander Scheinker

In this paper, we study Mahalanobis-guided latent out-of-distribution (OOD) detection for test-time RL controller switching in nonlinear time-varying systems. RL controllers can qu…

cs.RO2026

Deep Reinforcement Learning for Robotic Manipulation under Distribution Shift with Bounded Extremum Seeking

Shaifalee Saxena, Rafael Fierro, Alexander Scheinker

Reinforcement learning has shown strong performance in robotic manipulation, but learned policies often degrade in performance when test conditions differ from the training distrib…

math.OC2026

Nested Extremum Seeking Converges to Stackelberg Equilibrium

Brad Ratto, Alan Williams, Miroslav Krstić +2

The nested Extremum Seeking (nES) algorithm is a model-free optimization method that has been shown to converge to a neighborhood of a Nash equilibrium. In this work, we demonstrat…

cs.LG2026

Improved Robustness of Deep Reinforcement Learning for Control of Time-Varying Systems by Bounded Extremum Seeking

Shaifalee Saxena, Alan Williams, Rafael Fierro +1

In this paper, we study the use of robust model independent bounded extremum seeking (ES) feedback control to improve the robustness of deep reinforcement learning (DRL) controller…