InfoCoBuild

6.832 Underactuated Robotics

6.832 Underactuated Robotics (Spring 2009, MIT OCW). Instructor: Professor Russell Tedrake. This course discusses nonlinear dynamics and control of underactuated mechanical systems, with an emphasis on machine learning methods. Topics include nonlinear dynamics of passive robots (walkers, swimmers, flyers), motion planning, partial feedback linearization, energy-shaping control, analytical optimal control, reinforcement learning/approximate optimal control, and the influence of mechanical design on control. Discussions include examples from biology and applications to legged locomotion, compliant manipulation, underwater robots, and flying machines. (from ocw.mit.edu)

Lecture 18 - Stochastic Gradient Descent 2


Go to the Course Home or watch other lectures:

Lecture 01 - Introduction
Lecture 02 - The Simple Pendulum
Lecture 03 - Optimal Control of the Double Integrator
Lecture 04 - Optimal Control of the Double Integrator (cont.)
Lecture 05 - Numerical Optimal Control (Dynamic Programming)
Lecture 06 - Acrobot and Cart-pole
Lecture 07 - Swing-up Control of Acrobot and Cart-pole Systems
Lecture 08 - Dynamic Programming (DP) and Policy Search
Lecture 09 - Trajectory Optimization
Lecture 10 - Trajectory Stabilization and Iterative Linear Quadratic Regulator
Lecture 11 - Walking
Lecture 12 - Walking (cont.)
Lecture 13 - Running
Lecture 14 - Feasible Motion Planning
Lecture 15 - Global Policies from Local Policies
Lecture 16 - Introducing Stochastic Optimal Control
Lecture 17 - Stochastic Gradient Descent
Lecture 18 - Stochastic Gradient Descent 2
Lecture 19 - Temporal Difference Learning
Lecture 20 - Temporal Difference Learning with Function Approximation
Lecture 21 - Policy Improvement
Lecture 22 - Actor-critic Methods
Lecture 23 - Case Studies in Computational Underactuated Control