Schedule

Section I: Basic Geometry for Robotics

1/10/2023

PDF (Part1)
PDF (Part2)

Introduction

syllabus, logistics, high-level framework of embodied AI

1/12/2023

PDF
Keynote

Linear Transformation

cont' of overview, linear transformation

1/17/2023

PDF
Keynote

Rotation

representation of rotation

1/19/2023

PDF
Keynote

Inverse Kinematics

spatial/body twist, Jacobian of kinematics chain, inverse kinematics

1/24/2023

HTML

Basics of Planning, Dynamics, and Control

concepts of planning, RRT, PRM, manipulator equation, PID controller

1/24/2023

HTML

Working in Embodied AI Environments

best practices of using robot simulators

Section II: Reinforcement Learning

1/31/2023

HTML

RL Framework (I)

Markov Decision Process

2/2/2023

HTML

RL Framework (II)

Q-learning, TD, MC

2/7/2023

HTML

Policy Gradient

policy gradient theorem, REINFORCE

2/9/2023

HTML

Advanced Policy Gradient

advantag, TRPO, PPO

2/14/2023

HTML

Advanced Off-Policy RL

double q-learning, TD(n), dueling network, etc

2/21/2023

HTML

Exploration

bandit, UCB1

2/23/2023

HTML

Exploration II

curiosity-driven exploration, soft actor-critic, structural environment modeling

2/28/2023

HTML

Model-based RL

Section III: Robot Learning

3/2/2023

PDF

Skill Learning & Chaining

Guest lecture (Jiayuan Gu)

3/7/2023

PDF

Learning from Demonstrations

Guest lecture (Tongzhou Mu)

3/9/2023

PDF

Softbody Manipulation

Guest lecture (Zhiao Huang)

3/14/2023

PDF

Visual Reinforcement Learning

Guest lecture (Zhan Ling)

3/16/2023

PDF

Generalizable Policy Learning

Guest lecture (Zhiwei Jia)

Machine Learning for Robotics

Robot Learning - Winter 2023

Schedule

Section I: Basic Geometry for Robotics

Section II: Reinforcement Learning

Section III: Robot Learning