Skip to content

New: New Lecture (June 30) !

Welcome

Welcome to Spring 2026 offering of Deep Reinforcement Learning course at Sharif University of Technology! We are excited to have you join us on this journey into the world of deep reinforcement learning.

Previous Course (Spring 2025): DeepRLCourse Spring 2025

Learning Objectives

  • Understand the fundamentals of reinforcement learning
  • Apply reinforcement learning to various domains
  • Use deep learning techniques to handle large state spaces in RL
  • Master the concepts and gain practical understanding of RL
  • Gain hands-on experience with important RL problems
  • Equip students with enough theoretical knowledge to understand research papers

Instructor

Schedule

Session #
Topic of the Session
Date
Deliverables
Session 1 Introduction to RL
3 اسفند
(Feb 22)
-
Session 2 Introduction to RL
5 اسفند
(Feb 24)
-
Session 3 Value Based
-
-
-
Session 4 Value Based
-
-
-
Session 5 Value Based
-
-
-
Session 6 Value Based
-
-
-
Session 7 Policy Based
-
-
-
Session 8 Policy Based
6 اردیبهشت
(April 26)
-
Session 9 Policy Based
8 اردیبهشت
(April 28)
Policy Based TA Session/HW2 Release
Session 10 Actor Critic
13 اردیبهشت
(May 3)
-
Session 11 Actor Critic
15 اردیبهشت
(May 5)
Actor Critic TA Session
Session 12 Model Based
20 اردیبهشت
(May 10)
-
Session 13 Model Based
22 اردیبهشت
(May 12)
-
Session 14 Multi-Armed Bandit
27 اردیبهشت
(May 17)
-
Session 15 Boundaries of regret
29 اردیبهشت
(May 19)
-
Session 16 Exploration in full RL
3 خرداد
(May 24)
-
Session 17 Exploration in full RL
5 خرداد
(May 26)
MAB TA Session
Session 18 Imitation Learning
10 خرداد
(May 31)
-
Session 19 Imitation and Inverse RL
12 خرداد
(June 3)
-
Session 20 Offline RL
17 خرداد
(June 7)
-
Session 21 Offline RL
19 خرداد
(June 9)
Midterm
Session 22 Meta Learning
24 خرداد
(June 14)
-
Session 23 Meta Learning
26 خرداد
(June 16)
-
Session 24 Multi Agent RL
31 خرداد
(June 21)
-
Session 25 Multi Agent RL
2 تیر
(June 23)
-
Session 26 Multi Agent RL
7 تیر
(June 28)
-
Session 27 Multi Agent RL
9 تیر
(June 30)
Final Exam

Logistics & Policies

  • Lectures: Held on Sundays and Tuesdays from 1:30 PM to 3:00 PM in room 102 of the CE department. (Online here!)

  • TA Sessions: Held on Saturdays from 6:00 PM to 7:30 PM Online here!

Late Submission Policy

  • Each student has 14 total late days for the course.
  • Up to 3 late days may be used per assignment.

Grading

The grading for the Deep Reinforcement Learning course is structured as follows:

Main Components

  • Homeworks: Eight homework assignments, each worth 1 point, plus an additional assignment worth 0.5 points.
  • Midterm: An online midterm examination followed by additional oral questioning. The material covered includes all topics from the beginning of the course up to and including Model Based Methods, including the content presented in the TA sessions.
  • Final: A comprehensive final examination primarily covering the material taught after the Model Based Methods section. Earlier topics may appear indirectly as prerequisite knowledge, but the exam will directly focus on concepts introduced after that point.
  • Project: A mini research project in Deep Reinforcement Learning (DRL). Further details and guidelines regarding the project will be announced soon.
Component Points Date Details
Homeworks 8.5 - 8 HWs * 1 each + 0.5
Midterm 5
22 خرداد
June 12
@ 09:00 AM
Final 7
28 تیر
July 19
@ 14:30 PM
Project 2.5
؟
(?)
-
Total 23 - -

Head Assistants

Teaching Assistants

  • Instructor Avatar

    Parsa Ghezelbash

    Teaching Assistant

  • Instructor Avatar

    Amir Kooshan Fattah

    Teaching Assistant

  • Instructor Avatar

    Mohammad Amin Abbasfar

    Teaching Assistant

  • Instructor Avatar

    Arian Komaei

    Teaching Assistant

  • Instructor Avatar

    Mazdak Teymourian

    Teaching Assistant

  • Instructor Avatar

    Ramtin Moslemi

    Teaching Assistant

  • Instructor Avatar

    Danial Parnian

    Teaching Assistant

  • Instructor Avatar

    Amirmahdi Meighani

    Teaching Assistant

  • Instructor Avatar

    Mobin Bagherian

    Teaching Assistant

  • Instructor Avatar

    Amir Malekhosseini

    Teaching Assistant

  • Instructor Avatar

    Ali Soltani

    Teaching Assistant

  • Instructor Avatar

    Mahshid Dehghani

    Teaching Assistant

  • Instructor Avatar

    Milad Hosseini

    Teaching Assistant

  • Instructor Avatar

    Alireza Nobakht

    Teaching Assistant

  • Instructor Avatar

    Amir Homayoun Sharifi-zadeh

    Teaching Assistant

  • Instructor Avatar

    Saeed Terik

    Teaching Assistant

  • Instructor Avatar

    Hamidreza Ebrahimpour

    Teaching Assistant

  • Instructor Avatar

    Arshia Izadyari

    Teaching Assistant

  • Instructor Avatar

    SeyedAhmad MousaviAwal

    Teaching Assistant

Acknowledgements

We would like to express our gratitude to the following individuals for their invaluable contributions to the Spring 2025 and 2024 offerings of this course. Their efforts have been instrumental in the development and success of this course.

Spring 2025
Arash Alikhani Soroush VafaeiTabar Amir Mohammad Izadi Abdollah Zohrabi Ahmad Karami SeyyedAli MirGhasemi Alireza Nobakht Amirabbas Afzali Amirhossein Asadi Amirreza Velaei Armin Saghafian Arshia Gharooni Behnia Soleymani Benyamin Naderi Dariush Jamshidian Faezeh Sadeghi Ghazal Hosseini Hamidreza Ebrahimpour Hesam Hosseini Mahyar Afshimehr Masoud Tahmasbi Milad Hosseini Mohammad Mohammadi MohammadHasan Abbasi Naseer Kazemi Nima Shirzadi Ramtin Moslemi Reza GhaderiZadeh
Spring 2024
Alireza Ghahremani Alireza Sakhaei Rad Amirhossein Mohammadpour Azari Amirmohammad Izadi Arian Ahadinia Armin Behnamnia Armin Saghefian Behnia Soleimani Hossein Jafariniya Mahdi Ghaznavi Mohammadhassan Alikhani Ramtin Moslemi

This offering and all of these changes are thanks to their effort in starting this course.