Schedule
Section I: Reinforcement Learning
4/2/2024
Introduction
syllabus, logistics, high-level framework of embodied AI
4/4/2024
RL Framework (I)
Markov Decision Process
4/9/2024
RL Framework (II)
Q-learning, TD, MC
4/11/2024
DQN and REINFORCE
Finite Action Space
4/16/2024
Advanced Policy Gradient Algorithms
Practical First-Order Policy Optimization, Efficient and Stable Policy Optimization
4/18/2024
Advanced Off-Policy RL
Key Ideas, Tricks, and Frameworks
4/23/2024
Exploration
Exploration, Multi-Armed Bandits, Intrinsic Rewards
4/25/2024
Model Based RL
Model Based RL
4/30/2024
Learning from Demonstrations
Imitation Learning, Offline RL, Data Collection
Section II: Basic Geometry for Robotics
5/2/2024
Rigid Transformation
Rigid Transformation
5/7/2024
Rotation
Rotation
5/9/2024
Robot Kinematics
Kinematics Equations, Forward Kinematics, Inverse Kinematics
5/14/2024
Screw and Twist (1)
Screw theory
5/16/2024
Screw and Twist (2)
Twist theory
5/21/2024
Dynamics (I)
Dynamics (I)
5/23/2024
Dynamics (II), Planning
Dynamics (II), Planning
5/28/2024
Dynamics (III)
Dynamics (III)
5/30/2024
Lagrangian
Lagrangian
6/4/2024
Control and Simulator Debugging
Plan and Control, Practices to Debug Simulators
6/6/2024
Optimal Control
HJB equation, LQR