Lecture Details

Days: Friday
Duration: 1:30 PM - 4:15 PM (Aug 18 - Dec 01)
Lecture Hall: Lattie Coor Hall 174 (Tempe)
Submissions: Canvas
Syllabus: Course Syllabus
Live Lecture: Zoom Link provided in Canvas
Contact info: atricham@asu...


Description

This course offers a comprehensive exploration of planning and learning methods in Artificial Intelligence (AI). Students will gain a deep understanding of how AI systems can make informed decisions, strategize effectively, and adapt in dynamic environments. The course covers both theoretical foundations and practical applications of planning and learning algorithms, empowering students with the skills to design intelligent systems capable of autonomous decision-making. Topics include reasoning about time and action, plan synthesis and execution, sequential decision support, and reinforcement learning.


Prerequisites :

It is highly recommended that students complete CSE 471: Introduction to AI or CSE 475: Foundations of Machine Learning in order to be successful in this course.


Course Schedule:

WEEK LECTURE IMPORTANT DATES NOTES
Week 1
08/18/2023
Intro to decision-making   Week 1 Lecture
Week 2
08/25/2023
Myopic planning
Pytorch Tutorial
  Week 2 Lecture
Pytorch Tutorial
Additional Reading :
Algorithms for Optimization:Section 15, Section 16
Week 3
09/01/2023
Myopic planning
Robot Planning tutorial
  Week 3 Lecture
ROS Tutorial
Week 4
09/08/2023
Non-myopic planning and reinforcement learning Assignment 1 released: 6th Sept Assignment 1 code files
Week 4 Lecture
Assignment 1 Part A solutions
Week 5
09/15/2023
Non-myopic planning and reinforcement learning   Week 5 Lecture
Additional Reading :
SayCan
Week 6
09/22/2023
Imitation learning for decision-making Assignment 1 Due Date: 19th Sept
Assignment 2 released: 20th Sept
Week 6 Lecture
Assignment 2 Guidelines
Week 7
09/29/2023
Imitation learning for decision-making Project team formation and idea Due date: 25th Sept
Project Proposal Presentation : 29th Sept
Week 7 Lecture
Project Guidelines
Project Report Template
Week 8
10/06/2023
Human-in-the-loop planning   Week 8 Lecture
Additional Reading :
InstructGPT
Week 9
10/13/2023
Human-in-the-loop planning Assignment 2 Part 1: Due on 13th Oct
Assignment 2 Part 2: Due on 15th Oct
Week 9 Lecture
Student Presentations- RL algorithms
Week 10
10/20/2023
Task and Motion planning   Week 10 Lecture
Week 11
10/27/2023
Task and Motion planning Project Progress Presentation : 27th Oct  
Week 12
11/03/2023
Multiagent planning and decision-making under uncertainty    
Week 13
11/10/2023
Veterans Day Observed
(Classes excused/University closed)
   
Week 14
11/17/2023
Classical planning and hierarchical planning/learning Assignment 3 released: 12th Nov  
Week 15
11/24/2023
Thanksgiving Holiday Observed
(Classes excused/University closed)
Assignment 3 Due Date: 27th Nov  
Week 16
12/01/2023
Project presentations Final Project Presentations : 1st Dec
Final Project Report : 3rd Dec
Project Guidelines

Textbook & Additional Reading :

Algorithms for Decision Making
Algorithms for Optimization
Artificial Intelligence: A Modern Approach (4th US edition)
Reinforcement Learning: An Introduction (2nd edition)


Teaching Team :

prof
Ransalu Senanayake
(Instructor)
E-mail: ransalu@asu...
Office hours: Fri, 11:00 AM - 12:00 PM
Virtual: Meeting Link
Yancheng Wang
Yancheng Wang
(Teaching Assistant)
E-mail: ywan1053@asu...
Office hours: Wed, 2:00 PM - 3:00 PM
Virtual: Meeting Link
Office: BYENG 211
Akshara
Akshara Trichambaram
(Instructional Assistant)
E-mail: atricham@asu...
Office hours: Mon, 11:00 AM - 12:00 PM
Virtual: Meeting Link
suresh
Suresh Kondepudi
(Grader)
E-mail: nkondepu@asu...
Office hours: Ad-hoc (post grading)
Harsh
Harsh Mankodiya
(Grader)
E-mail: hmankodi@asu...
Office hours: Ad-hoc (post grading)