4 papers
Amortising Trajectory Optimisation for Residual MPC via Implicit Contact Differentiation
Daniel Layeghi, Thomas Corbères, Calum Arnott +4
Differentiable simulation can accelerate contact-rich trajectory optimisation by exposing local sensitivities of task outcomes to controls. Existing approaches either use finite di…
Learning Long-Horizon Robot Manipulation Skills via Privileged Action
Xiaofeng Mao, Yucheng Xu, Zhaole Sun +3
Long-horizon contact-rich tasks are challenging to learn with reinforcement learning, due to ineffective exploration of high-dimensional state spaces with sparse rewards. The learn…
Neural Lyapunov and Optimal Control
Daniel Layeghi, Steve Tonneau, Michael Mistry
Despite impressive results, reinforcement learning (RL) suffers from slow convergence and requires a large variety of tuning strategies. In this paper, we investigate the ability o…
Optimal Control via Combined Inference and Numerical Optimization
Daniel Layeghi, Steve Tonneau, Michael Mistry
Derivative based optimization methods are efficient at solving optimal control problems near local optima. However, their ability to converge halts when derivative information vani…