Showing 2026Show all
3 papers · 1 filter
cs.RO2026
SPARSER: Sparse Variable Projection by Exploiting Separable Structure in Robotic Perception
Nikolas R. Sanderson, Andrew Fishberg, Haoyu Han +5
Robotic perception often requires solving large nonlinear least-squares (NLS) problems. While sparsity has been widely exploited to scale solvers, a complementary and underused str…
cs.LG2026
Tempered Sequential Monte Carlo for Trajectory and Policy Optimization with Differentiable Dynamics
Heng Yang
We propose a sampling-based framework for finite-horizon trajectory and policy optimization under differentiable dynamics by casting controller design as inference. Specifically, w…
math.OC2026
Non-Uniform Noise-to-Signal Ratio in the REINFORCE Policy-Gradient Estimator
Haoyu Han, Heng Yang
Policy-gradient methods are widely used in reinforcement learning, yet training often becomes unstable or slows down as learning progresses. We study this phenomenon through the no…