Benjamin Recht: Optimization Perspectives on Learning to Control (ICML 2018 tutorial)
Abstract:
Given the dramatic successes in machine learning over the past half decade, there has been a resurgence of interest in applying learning techniques to continuous control problems in robotics, self-driving cars, and unmanned aerial vehicles. Though such applications appear to be straightforward generalizations of reinforcement learning, it remains unclear which machine learning tools are best equipped to handle decision making, planning, and actuation in highly uncertain dynamic environments.
This tutorial will survey the foundations required to build machine learning systems that reliably act upon the physical world. The primary technical focus will be on numerical optimization tools at the interface of statistical learning and dynamical systems. We will investigate how to learn models of dynamical systems, how to use data to achieve objectives in a timely fashion, how to balance model specification and system controllability, and how to safely acquire new information to improve performance. We will close by listing several exciting open problems that must be solved before we can build robust, reliable learning systems that interact with an uncertain environment.
Presented by Benjamin Recht (UC Berkeley)
Видео Benjamin Recht: Optimization Perspectives on Learning to Control (ICML 2018 tutorial) канала Steven Van Vaerenbergh
Given the dramatic successes in machine learning over the past half decade, there has been a resurgence of interest in applying learning techniques to continuous control problems in robotics, self-driving cars, and unmanned aerial vehicles. Though such applications appear to be straightforward generalizations of reinforcement learning, it remains unclear which machine learning tools are best equipped to handle decision making, planning, and actuation in highly uncertain dynamic environments.
This tutorial will survey the foundations required to build machine learning systems that reliably act upon the physical world. The primary technical focus will be on numerical optimization tools at the interface of statistical learning and dynamical systems. We will investigate how to learn models of dynamical systems, how to use data to achieve objectives in a timely fashion, how to balance model specification and system controllability, and how to safely acquire new information to improve performance. We will close by listing several exciting open problems that must be solved before we can build robust, reliable learning systems that interact with an uncertain environment.
Presented by Benjamin Recht (UC Berkeley)
Видео Benjamin Recht: Optimization Perspectives on Learning to Control (ICML 2018 tutorial) канала Steven Van Vaerenbergh
Показать
Комментарии отсутствуют
Информация о видео
4 сентября 2018 г. 18:28:31
02:05:38
Другие видео канала
Reinforcement Learning: Machine Learning Meets Control TheoryRecent Advances in Integrating Machine Learning and Combinatorial Optimization - Tutorial at AAAI-21Introduction to Trajectory OptimizationBYOL: Bootstrap Your Own Latent: A New Approach to Self-Supervised Learning (Paper Explained)Emo Todorov (University of Washington): "Acceleration-based methods"Reliability Growth: Concepts, Strategy, Duane Model and Application Case StudyMotor Control Design with MATLAB and SimulinkReinforcement Learning in 3 Hours | Full Course using PythonRobust Learning via Robust Optimization - Stefanie JegelkaVariational Inference: Foundations and Modern Methods (NIPS 2016 tutorial)On Evaluating Adversarial RobustnessSafe Learning-based Control Using Gaussian Processes @ IFAC2020Ian Goodfellow: Adversarial Machine Learning (ICLR 2019 invited talk)Federated Learning: Machine Learning on Decentralized Data (Google I/O'19)ICML 2018: Tutorial Session: Optimization Perspectives on Learning to ControlRay for Reinforcement Learning | UC Berkeley RISELabNonparametric Bayesian Methods: Models, Algorithms, and Applications IMIT 6.S191: Reinforcement LearningICML 2017 Tutorial: Recent Advances in Stochastic Convex and Non-Convex Optimization (audio fixed)Graph neural networks: Variations and applications