9 papers
Your Model Already Knows: Attention-Guided Safety Filter for Vision-Language-Action Models
Seongbin Park, Fan Zhang, Baharan Mirzasoleiman +2
Vision-Language-Action (VLA) models have demonstrated impressive end-to-end performance across a variety of robotic manipulation tasks. However, these policies offer no guarantees…
Scalar Federated Learning for Linear Quadratic Regulator
Mohammadreza Rostami, Shahriar Talebi, Solmaz S. Kia
We propose ScalarFedLQR, a communication-efficient federated algorithm for model-free learning of a common policy in linear quadratic regulator (LQR) control of cooperative agents.…
Learning Kalman Policy for Singular Unknown Covariances via Riemannian Regularization
Larsen Bier, Shahriar Talebi
Kalman filtering is a cornerstone of estimation theory, yet learning the optimal filter under unknown and potentially singular noise covariances remains a fundamental challenge. In…
Hereditary Geometric Meta-RL: Nonlocal Generalization via Task Symmetries
Paul Nitschke, Shahriar Talebi
Meta-Reinforcement Learning (Meta-RL) commonly generalizes via smoothness in the task encoding. While this enables local generalization around each training task, it requires dense…
Ergodic-Risk Constrained Policy Optimization: The Linear Quadratic Case
Shahriar Talebi, Na Li
Risk-sensitive control balances performance with resilience to unlikely events in uncertain systems. This paper introduces ergodic-risk criteria, which capture long-term cumulative…
Risk-sensitive Affine Control Synthesis for Stationary LTI Systems
Yang Hu, Shahriar Talebi, Na Li
To address deviations from expected performance in stochastic systems, we propose a risk-sensitive control synthesis method to minimize certain risk measures over the limiting stat…
Ergodic-risk Criterion for Stochastically Stabilizing Policy Optimization
Shahriar Talebi, Na Li
This paper introduces ergodic-risk criteria, which capture long-term cumulative risks associated with controlled Markov chains through probabilistic limit theorems--in contrast to…
Learning Low-dimensional Latent Dynamics from High-dimensional Observations: Non-asymptotics and Lower Bounds
Yuyang Zhang, Shahriar Talebi, Na Li
In this paper, we focus on learning a linear time-invariant (LTI) model with low-dimensional latent variables but high-dimensional observations. We provide an algorithm that recove…
Policy Optimization in Control: Geometry and Algorithmic Implications
Shahriar Talebi, Yang Zheng, Spencer Kraisler +2
This survey explores the geometric perspective on policy optimization within the realm of feedback control systems, emphasizing the intrinsic relationship between control design an…