4 papers
Error whitening: Why Gauss-Newton outperforms Newton
Maricela Best McKay, Nathan P. Lawrence, Brian Wetton +1
The Gauss-Newton matrix is widely viewed as a positive semidefinite approximation of the Hessian, yet mounting empirical evidence shows that Gauss-Newton descent outperforms Newton…
A view on learning robust goal-conditioned value functions: Interplay between RL and MPC
Nathan P. Lawrence, Philip D. Loewen, Michael G. Forbes +2
Reinforcement learning (RL) and model predictive control (MPC) offer a wealth of distinct approaches for automatic decision-making under uncertainty. Given the impact both fields h…
DiLQR: Differentiable Iterative Linear Quadratic Regulator via Implicit Differentiation
Shuyuan Wang, Philip D. Loewen, Michael Forbes +2
While differentiable control has emerged as a powerful paradigm combining model-free flexibility with model-based efficiency, the iterative Linear Quadratic Regulator (iLQR) remain…
Guiding Reinforcement Learning with Incomplete System Dynamics
Shuyuan Wang, Jingliang Duan, Nathan P. Lawrence +4
Model-free reinforcement learning (RL) is inherently a reactive method, operating under the assumption that it starts with no prior knowledge of the system and entirely depends on…