paper-with-me

홈 › Papers

Scaling up and Stabilizing Differentiable Planning with Implicit Differentiation

2022-10-24 · Linfeng Zhao, Huazhe Xu, Lawson L. S. Wong

Differentiable planning promises end-to-end differentiability and adaptivity. However, an issue prevents it from scaling up to larger-scale problems: they need to differentiate through forward iteration layers to compute gradients, which couples forward computation and backpropagation, and needs to balance forward planner performance and computational cost of the backward pass. To alleviate this issue, we propose to differentiate through the Bellman fixed-point equation to decouple forward and backward passes for Value Iteration Network and its variants, which enables constant backward cost (in planning horizon) and flexible forward budget and helps scale up to large tasks. We study the convergence stability, scalability, and efficiency of the proposed implicit version of VIN and its variants and demonstrate their superiorities on a range of planning tasks: 2D navigation, visual navigation, and 2-DOF manipulation in configuration space and workspace.

📄 PDF Abstract BibTeX arXiv:2210.13542

Code (0)

등록된 구현이 없습니다.

Tasks

Visual Navigation

Similar Papers 제목 키워드 기반

Efficient differentiable quadratic programming layers: an ADMM approach

2021-12-14 · Andrew Butler, Roy Kwon

Recent advances in neural-network architecture allow for seamless integration of convex optimization problems as differentiable layers in an end-to-end trainable neural network. Integrating medium and large scale quadrat…

Portfolio Optimization

Differentiable Implicit Soft-Body Physics

2021-02-11 · Junior Rojas, Eftychios Sifakis, Ladislav Kavan

We present a differentiable soft-body physics simulator that can be composed with neural networks as a differentiable layer. In contrast to other differentiable physics approaches that use explicit forward models to defi…

Numerical Integration

Infinite-Horizon Differentiable Model Predictive Control

2020-01-07 · ICLR 2020 1 · Sebastian East, Marco Gallieri, Jonathan Masci, Jan Koutnik 외

This paper proposes a differentiable linear quadratic Model Predictive Control (MPC) framework for safe imitation learning. The infinite-horizon cost is enforced using a terminal cost function obtained from the discrete-…

Imitation LearningmodelModel Predictive Control

TurboMPC: Fast, Scalable, and Differentiable Model Predictive Control on the GPU

2026-06-23 · Gabriel Bravo-Palacios, Jianghan Zhang, Zachary Pestrikov, Brian Plancher 외 arxiv

Robotics increasingly relies on GPUs for parallel simulation, large-scale learning, and neural-network inference. For model predictive control (MPC) to scale with this paradigm, solvers must run efficiently on this hardw…

Reinforcement Learning

Differentiable Programming of Isometric Tensor Networks

2021-10-08 · Chenhua Geng, Hong-Ye Hu, Yijian Zou

Differentiable programming is a new programming paradigm which enables large scale optimization through automatic calculation of gradients also known as auto-differentiation. This concept emerges from deep learning, and …

Tensor Networks