Stanford CS234: Reinforcement Learning | Winter 2019 | Lecture 12 - Fast Rei...

Professor Emma Brunskill
Assistant Professor, Computer Science
Stanford AI for Human Impact Lab
Stanford Artificial Intelligence Lab
Statistical Machine Learning Group

Numerically Linearizing a Dynamic System

In this video we show how to linearize a dynamic system using numerical techniques. In other words, the linearization process does not require an analytical description of the system. This...

An efficient orientation filter for inertial and inertial/magnetic sensor ar...

This report presents a novel orientation filter applicable to IMUs consisting of tri-axis gyroscopes and accelerometers, and MARG sensor arrays that also include tri-axis magnetometers. The...

Data-Driven Control: Balanced Models with ERA

In this lecture, we connect the eigensystem realization algorithm (ERA) to balanced proper orthogonal decomposition (BPOD). In particular, if enough data is collected, then ERA produces...

How the Flight Controller Code Works - dRehmFlight VTOL

This video will walk you through the flight controller code of dRehmFlight VTOL to give you a better understanding of the contents and structure. The hope is that it will cover almost...

Data-Driven Control: The Goal of Balanced Model Reduction

In this lecture, we discuss the overarching goal of balanced model reduction: Identifying key states that are most jointly controllable and observable, to capture the most input—output...

Inner Products in Hilbert Space

This video will show how the inner product of functions in Hilbert space is related to the standard inner product of vectors of data.

SVD: Optimal Truncation [Matlab]

This video describes how to optimally truncate the singular value decomposition (SVD) for noisy data (Matlab code).

Stanford CS234: Reinforcement Learning | Winter 2019 | Lecture 15 - Batch Re...

Professor Emma Brunskill
Assistant Professor, Computer Science
Stanford AI for Human Impact Lab
Stanford Artificial Intelligence Lab
Statistical Machine Learning Group

Teaching resources for a reinforcement learning course

Teaching resources by Dimitri P. Bertsekas for reinforcement learning courses. The website has links for freely available textbooks (for instructional purposes), videolectures, and course...

Ratio Control and Scaled Signal Calculations

When and how to use ratio, and how to implement within standard scaled signals

Data-Driven Control: Balancing Example

In this lecture, we give an example of how a change of coordinates can balance the controllability and observability of an input—output system.

Dynamic Mode Decomposition (Code)

In this video, we code up the dynamic mode decomposition (DMD) in Matlab and use it to analyze the fluid flow past a circular cylinder at low Reynolds number.

Singular Value Decomposition (SVD): Matrix Approximation

This video describes how the singular value decomposition (SVD) can be used for matrix approximation.

Linear Regression 1 [Matlab]

This video describes how the singular value decomposition (SVD) can be used for linear regression in Matlab (part 1).

Stanford CS234: Reinforcement Learning | Winter 2019 | Lecture 9 - Policy Gr...

Professor Emma Brunskill

Assistant Professor, Computer Science

Stanford AI for Human Impact Lab

Stanford Artificial Intelligence Lab

Statistical Machine Learning Group

RL Course by David Silver - Lecture 5: Model Free Control

Dives into On Policy Monte-Carlo Control and Temporal Difference Learning, as well as Off-Policy Learning.

Euler Angles and the Euler Rotation Sequence

In this video we discuss how Euler angles are used to define the relative orientation of one coordinate frame to another.

Data-Driven Control: Eigensystem Realization Algorithm

In this lecture, we introduce the eigensystem realization algorithm (ERA), which is a purely data-driven algorithm to obtain balanced input—output models from impulse response data. ERA was...

Parseval's Theorem

Parseval's theorem is an important result in Fourier analysis that can be used to put guarantees on the accuracy of signal approximation in the Fourier domain.

SVD: Eigenfaces 1 [Python]

This video describes how the singular value decomposition (SVD) can be used to efficiently represent human faces, in the so-called "eigenfaces" (Python code, part 1).

Principal Component Analysis (PCA) [Matlab]

This video describes how the singular value decomposition (SVD) can be used for principal component analysis (PCA) in Matlab.

Stanford CS234: Reinforcement Learning | Winter 2019 | Lecture 4 - Model Fre...

Professor Emma Brunskill
Assistant Professor, Computer Science
Stanford AI for Human Impact Lab
Stanford Artificial Intelligence Lab
Statistical Machine Learning Group

RL Course by David Silver - Lecture 10: Classic Games

An overview of Game Theory, minimax search, self-play and imperfect information games.

The Navigation Equations: Computing Position North, East, and Down

In this video we show how to compute the inertial velocity of a rigid body in the vehicle-carried North, East, Down (NED) frame. This is achieved by rotating the velocity expressed in the...