YoVDO

2019 ADSI Summer Workshop- Algorithmic Foundations of Learning and Control

Offered By: Paul G. Allen School via YouTube

Tags

Machine Learning Courses Reinforcement Learning Courses Control Systems Courses Algorithmic Design Courses Thompson Sampling Courses

Course Description

Overview

Explore the concept of "Exploration via Randomized Value Functions" in this 50-minute lecture from the 2019 ADSI Summer Workshop on Algorithmic Foundations of Learning and Control. Delve into topics such as deep exploration, linear sanity checking, stochastic policies, and Thompson sampling. Examine algorithmic ideas, intuition, and theory behind shortest path problems, episodic reinforcement learning, and model-based tabular learning. Investigate scalable approximations, value function approximations, and the real challenges facing the field. Gain insights into deep questions surrounding exploration in learning and control algorithms.

Syllabus

Introduction
Balancing
Outline
Deep Exploration
Large Theory
Linear sanity checking
The problem
Stochastic policies
Algorithm template
greedy
Thompson sampling
Does it work
One algorithmic idea
Intuition
Theory
Shortest Path
episodic reinforcement learning
modelbased tabular learning
scalable approximations
value function approximations
the real challenge
deep questions


Taught by

Paul G. Allen School

Related Courses

Computing Form and Shape: Python Programming with the Rhinoscript Library
Rhode Island School of Design via Kadenze
Algorithms and Data Structures
University of California, San Diego via edX
Learning Grasshopper
LinkedIn Learning
Stay Ahead in Architecture with Algorithmic Design
LinkedIn Learning
Learning Algorithmic Design with Grasshopper
LinkedIn Learning