16-311 Introduction to Robotics
         Main         Schedule         Homework         Labs         Links

  16-311 Homework 4

16-311 Homework 4


Learning Objectives

  1. Implement a discounted reward policy for a simplified motion planning problem by hand.
  2. Think critically about path planning and reward applications.
  3. Implement imitation learning for a cartpole.
  4. Observe the effects of policy improvement.

Background

Homework Requirements

The specifications for the homework are here hw4.pdf

The starter code for the homework is here hw4_starter-code.zip

Extensions

Last updated 02/10/2022 by Ananya Rao
(c) 1999-2022: Howie Choset, Carnegie Mellon