[go: up one dir, main page]
Scribd
Upload
22 views3 pages

Gujarat Technological University: Bachelor of Engineering Syllabus Subject Code: Subject Name

Uploaded by

Smit Patel

Pdf about artificial intelligence

Copyright:

© All Rights Reserved
Download as PDF, TXT or read online from Scribd
Download as pdf or txt

Gujarat Technological University: Bachelor of Engineering Syllabus Subject Code: Subject Name

Uploaded by

Smit Patel
22 views3 pages
Pdf about artificial intelligence

Original Title

3174208

Copyright

© © All Rights Reserved

Available Formats

PDF, TXT or read online from Scribd

Did you find this document useful?

Is this content inappropriate?

Pdf about artificial intelligence

Copyright:

© All Rights Reserved
Download as PDF, TXT or read online from Scribd
Download as pdf or txt
22 views3 pages

Gujarat Technological University: Bachelor of Engineering Syllabus Subject Code: Subject Name

Uploaded by

Smit Patel
Pdf about artificial intelligence

Copyright:

© All Rights Reserved
Download as PDF, TXT or read online from Scribd
Download as pdf or txt
You are on page 1/ 3

GUJARAT TECHNOLOGICAL UNIVERSITY

BACHELOR OF ENGINEERING SYLLABUS


Subject Code : 3174208
Subject Name : Reinforcement Learning

WEF Academic Year : 2023-24


Semester : 7
Category of the Course : Professional Elective - VI

Prerequisite: Linear algebra, probability, statistics, machine learning

Rationale : In this course, we will investigate the process of learning through an agent's mistakes. This is
very dissimilar to supervised machine learning and more closely resembles how people learn via
experience. The focus of Reinforcement Learning (RL) is on issues that call for a series of decisions to be
made in order. The fundamentals of reinforcement learning are the focus of this course.

Course Scheme :
Total
Teaching Scheme Assessment Pattern and Marks
Credits Total
Theory Practical Marks
L T PR C
ESE (E) PA(M) ESE (V) PA (I)
3 0 2 4 70 30 30 20 150

Course Content :
Sr. No. of % of
Course Content
No. Hours Weightage
Introduction
Course logistics and overview. Origin and history of Reinforcement
1 6 15
Learning research. Its connections with other related fields and with
different branches of machine learning.
Probability Primer
Brush up of Probability concepts - Axioms of probability, concepts of
2 random variables, PMF, PDFs, CDFs, Expectation. Concepts of joint and 6 15
multiple random variables, joint, conditional and marginal distributions.
Correlation and independence.
Markov Decision Process
Introduction to RL terminology, Markov property, Markov chains,
3 Markov reward process (MRP). Introduction to and proof of Bellman 8 20
equations for MRPs along with proof of existence of solution to Bellman
equations in MRP. Introduction to Markov decision process (MDP), state

https://syllabus.gtu.ac.in/ Page 1
GUJARAT TECHNOLOGICAL UNIVERSITY
BACHELOR OF ENGINEERING SYLLABUS
Subject Code : 3174208
Subject Name : Reinforcement Learning

and action value functions, Bellman expectation equations, optimality of


value functions and policies, Bellman optimality equations.
Prediction and Control by Dynamic Programing
Overiew of dynamic programing for MDP, definition and formulation of
planning in MDPs, principle of optimality, iterative policy evaluation,
4 policy iteration, value iteration, Banach fixed point theorem, proof of 8 20
contraction mapping property of Bellman expectation and optimality
operators, proof of convergence of policy evalutation and value iteration
algorithms, DP extensions.
Monte Carlo Methods for Model Free Prediction and Control
Overiew of Monte Carlo methods for model free RL, First visit and every
5 6 15
visit Monte Carlo, Monte Carlo control, On policy and off policy learning,
Importance sampling.
TD Methods
Incremental Monte Carlo Methods for Model Free Prediction, Overview
6 TD(0), TD(1) and TD(λ), k-step estimators, unified view of DP, MC and 6 15
TD evaluation methods, TD Control methods - SARSA, Q-Learning and
their variants.

Reference Book:
 “Reinforcement Learning”, Sutton and Barto, MIT Press, 2018
 “An Introduction to Internet of Things: Connecting Devices, Edge Gateway, and Cloud with
Applications”, Rahul Dubey, Cengage India Publication
 "Reinforcement Learning: Theory and Algorithms" Alekh Agarwal, Nan Jiang, Sham
Kakade, and John Langford
 Machine Learning: A Reinforcement Approach" by Satinder Singh and Sanjay Lal
 "Artificial Intelligence: Reinforcement Learning in Python: Complete guide to artificial
intelligence and machine learning", Lazy Programmer, Kindle Edition

Course Outcome:
After Completion of the Course, Student will able to:
No Course Outcomes RBT Level*
01 Learn how to define RL tasks and the core principals behind the RL, RM
02 Understand the basics of probability and distribution functions UN
03 Understand and work with tabular methods to solve classical control problems UN
04 Apply approximate methods to solve problems AP

https://syllabus.gtu.ac.in/ Page 2
GUJARAT TECHNOLOGICAL UNIVERSITY
BACHELOR OF ENGINEERING SYLLABUS
Subject Code : 3174208
Subject Name : Reinforcement Learning

*RM: Remember, UN: Understand, AP: Apply, AN: Analyze, EL: Evaluate, CR: Create

Suggested Course Practical List :


Implement 10 practical which are covering basics of course.

List of Laboratory/Learning Resources Required :


https://www.synopsys.com/ai/what-is-reinforcement-learning.html
https://www.simplilearn.com/tutorials/machine-learning-tutorial/reinforcement-learning
https://www.udemy.com/course/beginner-master-rl-1/
https://www.guru99.com/reinforcement-learning-tutorial.html
https://towardsdatascience.com/reinforcement-learning-101-e24b50e1d292

*******

https://syllabus.gtu.ac.in/ Page 3

You might also like