Scribd
Upload
166 views2 pages

E1 277 January-April 3:1 Reinforcement Learning: Instructor

This document provides information about a reinforcement learning course including the instructor, teaching assistants, schedule, prerequisites, syllabus, course outcomes, grading policy, and resources. The course deals with probabilistic models and algorithms for dynamic decision making under uncertainty, covering topics like stochastic dynamic programming, Q-learning, temporal difference learning, and actor-critic algorithms. Students will learn modeling and analysis techniques that can be applied to problems involving sequential decision making and will gain an understanding of commonly used reinforcement learning algorithms.

Uploaded by

praveen
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
166 views2 pages

E1 277 January-April 3:1 Reinforcement Learning: Instructor

This document provides information about a reinforcement learning course including the instructor, teaching assistants, schedule, prerequisites, syllabus, course outcomes, grading policy, and resources. The course deals with probabilistic models and algorithms for dynamic decision making under uncertainty, covering topics like stochastic dynamic programming, Q-learning, temporal difference learning, and actor-critic algorithms. Students will learn modeling and analysis techniques that can be applied to problems involving sequential decision making and will gain an understanding of commonly used reinforcement learning algorithms.

Uploaded by

praveen
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

E1 277 January-April 3:1

Reinforcement Learning

Instructor
Shalabh Bhatnagar
Email: [email protected]
Teaching Assistant
Sindhu P.R., Raghuram Bharadwaj
Email: [email protected], [email protected]

Department: Computer Science and Automation


Course Time: Tuesday/Thursday 9:30-11:00
Lecture venue: CSA 252
Detailed Course Page:

Announcements

Brief description of the course


The course deals with probabilistic models for problems of dynamic decision making under uncertainty.

Stochastic dynamic programming is a general framework for modelling such problems. However, one requires

knowledge of transition probabilities (i.e., the system dynamics) as well as the associated cost function. Both

of these quantities are normally not known and one only has access to data that is available from the

experiment. For instance, one may not know the transition probabilities but one may see what the next state is

given the current state and the action or control chosen. The course deals with building first the model based

dynamic programming techniques and subsequently the model free, data driven algorithms, and deals with the

theoretical foundations of these.


Prerequisites
Any student who has done the course E0 232 -- Probability and Statistics or an equivalent probability course.
Syllabus
Introduction to reinforcement learning, introduction to stochastic dynamic programming, finite and infinite

horizon models, the dynamic programming algorithm, infinite horizon discounted cost and average cost

Page 1/2
problems, numerical solution methodologies, full state representations, function approximation techniques,

approximate dynamic programming, partially observable Markov decision processes, Q-learning, temporal

difference learning, actor-critic algorithms.


Course outcomes
The students will get to know modelling and analysis tools and techniques for problems of dynamic decision

making under uncertainty. They will know the algorithms they can apply when faced with such problems and

the convergence and accuracy guarantees that such algorithms would provide.
Grading policy
Two mid term exams, One course project, and One final exam
Assignments

Resources

Page 2/2

You might also like