Deep Learning Course (NYU, Spring 2020) - Week 10 – Practicum: The Truck Backer-Upper

5.0 (0)

8 learners

What you'll learn

This course includes

42.5 hours of video
Certificate of completion
Access on mobile and TV

Summary

Keywords

Deep Learning Yann LeCun PyTorch NYU model predictive control RL Reinforcement Learning controller policy world model predictive model forward model

Full Transcript

Course website: http://bit.ly/DLSP20-web Playlist: http://bit.ly/pDL-YouTube Speaker: Alfredo Canziani Week 10: http://bit.ly/DLSP20-10 0:00:00 – Week 10 – Practicum PRACTICUM: http://bit.ly/DLSP20-10-3 During this week’s practicum, we explore the Truck Backer-Upper (Nguyen & Widrow, ‘90). This problem shows how to solve a non-linear control problem using neural networks. We learn a model of a truck’s kinematics, and optimize a controller through this learned model, finding that the controller is able to learn complex behaviors through purely observational data. 0:00:59 – Set up and visualization of the self-learning problem "The Truck Backer-Upper" 0:19:44 – Training the Neural-nets Model for Emulator and Controller 0:38:48 – Understanding of the PyTorch code

Continue this lesson in the app

Install CourseHive on Android or iOS to keep learning while you move.

Related Courses

30-Day Beginner Guitar Challenge for New Players

Master the Guitar in 30 Days: Your Ultimate Beginner Challenge! Unleash your inner guitarist with step-by-step lessons designed to transform you from novice to confident player. Join Your Guitar Academy and kickstart your musical journey today!

⭐ 4.3

36 ratings

7 hours