paper-with-me

Papers

Deluca -- A Differentiable Control Library: Environments, Methods, and Benchmarking

2021-02-19 · Paula Gradu, John Hallman, Daniel Suo, Alex Yu, Naman Agarwal, Udaya Ghai, Karan Singh, Cyril Zhang, Anirudha Majumdar, Elad Hazan

We present an open-source library of natively differentiable physics and robotics environments, accompanied by gradient-based control methods and a benchmark-ing suite. The introduced environments allow auto-differentiation through the simulation dynamics, and thereby permit fast training of controllers. The library features several popular environments, including classical control settings from OpenAI Gym. We also provide a novel differentiable environment, based on deep neural networks, that simulates medical ventilation. We give several use-cases of new scientific results obtained using the library. This includes a medical ventilator simulator and controller, an adaptive control method for time-varying linear dynamical systems, and new gradient-based methods for control of linear dynamical systems with adversarial perturbations.

📄 PDF Abstract BibTeX arXiv:2102.09968

Code (1)

google/deluca 공식 구현 jax

Tasks

BenchmarkingOpenAI Gym

Similar Papers 제목 키워드 기반

Differentiable Computational Geometry for 2D and 3D machine learning

2020-11-22 · Yuanxin Zhong

With the growth of machine learning algorithms with geometry primitives, a high-efficiency library with differentiable geometric operators are desired. We present an optimized Differentiable Geometry Algorithm Library (D…

BIG-bench Machine LearningGPU

Differentiable and Learnable Robot Models

2022-02-22 · Franziska Meier, Austin Wang, Giovanni Sutanto, Yixin Lin 외

Building differentiable simulations of physical processes has recently received an increasing amount of attention. Specifically, some efforts develop differentiable robotic physics engines motivated by the computational …

DDSP: Differentiable Digital Signal Processing

2020-01-14 · ICLR 2020 1 · Jesse Engel, Lamtharn Hantrakul, Chenjie Gu, Adam Roberts

Most generative models of audio directly generate samples in one of two domains: time or frequency. While sufficient to express any signal, these representations are inefficient, as they do not utilize existing knowledge…

Audio GenerationAudio Synthesis

NeuralFluid: Neural Fluidic System Design and Control with Differentiable Simulation

2024-05-22 · Yifei Li, Yuchen Sun, Pingchuan Ma, Eftychios Sifakis 외

We present a novel framework to explore neural control and design of complex fluidic systems with dynamic solid boundaries. Our system features a fast differentiable Navier-Stokes solver with solid-fluid interface handli…

Differentiable Information Enhanced Model-Based Reinforcement Learning

2025-03-03 · Xiaoyuan Zhang, Xinyan Cai, Bo Liu, Weidong Huang 외

Differentiable environments have heralded new possibilities for learning control policies by offering rich differentiable information that facilitates gradient-based methods. In comparison to prevailing model-free reinfo…

Deformable Object ManipulationmodelModel-based Reinforcement Learningreinforcement-learning+1