📣 Course Notes for <Week 4: Advanced Methods> are Out!
🌐 https://deeprlcourse.github.io/course_notes/advanced
🌐 https://deeprlcourse.github.io/course_notes/advanced
deeprlcourse.github.io
Week 4: Advanced Methods - Deep RL Course
This page delves into advanced reinforcement learning methods, focusing on actor-critic algorithms such as PPO, DDPG, and SAC. It explores key concepts like Reward-to-Go, Advantage Estimation, and Generalized Advantage Estimation (GAE), providing theoretical…
❤2
📣 Midterm Q&A Session with Prof. Rohban
We’ll be holding a Q&A session with Prof. Rohban this Tuesday from 12:30 to 1:15 PM, focused on questions related to the midterm.
If you have any doubts or need clarification before the exam, this is a great chance to ask!
🗓 Date: Tuesday
🕧 Time: 12:30 – 1:15 PM
👨🏫 Host: Prof. Mohammad Hossein Rohban
Make sure to join! 🚀
We’ll be holding a Q&A session with Prof. Rohban this Tuesday from 12:30 to 1:15 PM, focused on questions related to the midterm.
If you have any doubts or need clarification before the exam, this is a great chance to ask!
🗓 Date: Tuesday
🕧 Time: 12:30 – 1:15 PM
👨🏫 Host: Prof. Mohammad Hossein Rohban
Make sure to join! 🚀
❤6👍1
Lecture_13_Summary.pdf
258.7 KB
🎓 Summary of Lecture 13 📚
🔗 Quiz Link: https://forms.gle/8ve6qcc41f4VSwceA
🕐 Deadline: 1:30 PM (before the class)
Stay on track and get it done! 🚀
🔗 Quiz Link: https://forms.gle/8ve6qcc41f4VSwceA
🕐 Deadline: 1:30 PM (before the class)
Stay on track and get it done! 🚀
❤2🫡1
Deep RL (Sp25)
📣 Midterm Q&A Session with Prof. Rohban We’ll be holding a Q&A session with Prof. Rohban this Tuesday from 12:30 to 1:15 PM, focused on questions related to the midterm. If you have any doubts or need clarification before the exam, this is a great chance…
📣 This session will be held in Class 201 of the CE Department
❤4
📣 Homework 7 is out!
⏰ Deadline: May 11 (۲۱ اردیبهشت) 11:59 PM
🌐 https://deeprlcourse.github.io/homeworks/week7
⏰ Deadline: May 11 (۲۱ اردیبهشت) 11:59 PM
🌐 https://deeprlcourse.github.io/homeworks/week7
deeprlcourse.github.io
HW7: Value-Based Theory - Deep RL Course
This page contains the homework assignment for Week 7 of the Deep Reinforcement Learning course, focusing on Value-Based Theory.
🫡2❤1
📣 Ghazal Hosseini, one of the designers of Homework 7, explains the homework for you:
🎥 https://www.youtube.com/watch?v=jcVc3TXnK6I
🎥 https://www.youtube.com/watch?v=jcVc3TXnK6I
YouTube
Homework 7 | Value-Based Theory | Spring 25
Presented by Ghazal Hosseini
🔗 https://www.linkedin.com/in/ghazal-hosseini-mighan-8b911823a
📂 Access the Homework:
🔗 https://deeprlcourse.github.io/homeworks/week7
Stay Connected:
✉️ deeprlcourse@gmail.com
🌐 https://deeprlcourse.github.io
📺 https://www…
🔗 https://www.linkedin.com/in/ghazal-hosseini-mighan-8b911823a
📂 Access the Homework:
🔗 https://deeprlcourse.github.io/homeworks/week7
Stay Connected:
✉️ deeprlcourse@gmail.com
🌐 https://deeprlcourse.github.io
📺 https://www…
❤2
📣 Screen Record of Midterm QA Session is Out!
🎥 https://www.youtube.com/watch?v=URna5SMXtTg
🎥 https://www.youtube.com/watch?v=URna5SMXtTg
YouTube
QA Session | Midterm | Spring 25 (Screen Record)
Welcome to the Midterm QA Session of our Spring 2025 Deep RL Course! 🚀
Stay Connected:
✉️ deeprlcourse@gmail.com
🌐 https://deeprlcourse.github.io
📺 https://www.youtube.com/@DeepRLCourse
🐦 https://x.com/DeepRLCourse
📢 https://news.1rj.ru/str/DeepRLCourse
Don't forget…
Stay Connected:
✉️ deeprlcourse@gmail.com
🌐 https://deeprlcourse.github.io
📺 https://www.youtube.com/@DeepRLCourse
🐦 https://x.com/DeepRLCourse
📢 https://news.1rj.ru/str/DeepRLCourse
Don't forget…
❤2
📣 Screen Record of Lecture 14 is Out!
🎥 https://www.youtube.com/watch?v=td1weQgnWMs
🎥 https://www.youtube.com/watch?v=td1weQgnWMs
YouTube
Lecture 14 | Value-Based Theory | Spring 25 (Screen Record)
Welcome to the 14th lecture of our Spring 2025 Deep RL Course! 🚀
In this session, we continue to dive into the Value-Based Theory🤖
💡 Want more resources?
Get the slides and extra goodies here:
🔗 https://deeprlcourse.github.io/lectures/week7
Stay Connected:…
In this session, we continue to dive into the Value-Based Theory🤖
💡 Want more resources?
Get the slides and extra goodies here:
🔗 https://deeprlcourse.github.io/lectures/week7
Stay Connected:…
❤3
Deep RL (Sp25)
📣 Homework 6 is out! ⏰ Deadline: Apr 6 (۱۷ فروردین) 11:59 PM (+3 Extra Days Until Hard Deadline!) 🌐 https://deeprlcourse.github.io/homeworks/week6
📣 Hard Deadline for Homework 6 is Today at 2:59 AM and the Solution will be released in the morning.
🫡2
📣 Course Notes for <Week 5: Model-Based Methods> are Out!
🌐 https://deeprlcourse.github.io/course_notes/model-based
🌐 https://deeprlcourse.github.io/course_notes/model-based
deeprlcourse.github.io
Week 5: Model-Based Methods - Deep RL Course
This page provides a comprehensive overview of Model-Based Reinforcement Learning (MBRL), covering foundational concepts, key methodologies, and modern algorithms. It explores the integration of planning and learning, dynamics model learning, and advanced…
🔥3
📣 Course Notes for <Week 6: Multi-Armed Bandits> are Out!
🌐 https://deeprlcourse.github.io/course_notes/bandits
🌐 https://deeprlcourse.github.io/course_notes/bandits
deeprlcourse.github.io
Week 6: Multi-Armed Bandits - Deep RL Course
This page provides an in-depth exploration of the Multi-Armed Bandit (MAB) problem, a foundational concept in reinforcement learning and decision-making under uncertainty. It covers the theoretical framework, key algorithms, and practical applications of…
❤2🔥2
📣 Midterm Exam
The midterm exam will be held tomorrow at 9:00 AM in the following classrooms:
🏫 Education Building (ساختمان آموزش)
🧾 Classrooms: 202 and 210
The midterm exam will be held tomorrow at 9:00 AM in the following classrooms:
🏫 Education Building (ساختمان آموزش)
🧾 Classrooms: 202 and 210
🫡2🔥1👏1
Lecture_14_Summary.pdf
462 KB
🎓 Summary of Lecture 14 📚
🔗 Quiz Link: https://forms.gle/VvEGDpQHpuxsuEKq7
🕐 Deadline: 1:30 PM (before the class)
Stay on track and get it done! 🚀
🔗 Quiz Link: https://forms.gle/VvEGDpQHpuxsuEKq7
🕐 Deadline: 1:30 PM (before the class)
Stay on track and get it done! 🚀
❤5
📣 "Value-Based Theory" Recitation
🕛 Tomorrow (Monday Apr 14th) at 6:00 PM
🧑🏻🏫 Ghazal Hosseini
🏬 Class 402
🧠 Don’t miss it—let's learn and explore together! 💡
🕛 Tomorrow (Monday Apr 14th) at 6:00 PM
🧑🏻🏫 Ghazal Hosseini
🏬 Class 402
🧠 Don’t miss it—let's learn and explore together! 💡
❤4
Lecture_15_Summary.pdf
402.7 KB
🎓 Summary of Lecture 15 📚
🔗 Quiz Link: https://forms.gle/71EzjipGKPATtU1x6
🕐 Deadline: 1:30 PM (before the class)
Stay on track and get it done! 🚀
🔗 Quiz Link: https://forms.gle/71EzjipGKPATtU1x6
🕐 Deadline: 1:30 PM (before the class)
Stay on track and get it done! 🚀
❤3😁2
📣 Please Give Us Feedback
🟢 Feedback Form for Recitation 5
🟢 Feedback Form for Workshop 5
🟢 Feedback Form for Recitation 6
🟢 Feedback Form for Workshop 6
🟢 Feedback Form for Homework 3
🟢 Feedback Form for Homework 4
🟢 Feedback Form for Homework 5
🟢 Feedback Form for Homework 6
⏰ Deadline: Apr 18, 12 Midnight
🟢 Feedback Form for Recitation 5
🟢 Feedback Form for Workshop 5
🟢 Feedback Form for Recitation 6
🟢 Feedback Form for Workshop 6
🟢 Feedback Form for Homework 3
🟢 Feedback Form for Homework 4
🟢 Feedback Form for Homework 5
🟢 Feedback Form for Homework 6
⏰ Deadline: Apr 18, 12 Midnight
❤3
📣 Visit to Taarlab (آزمایشگاه تعامل انسان و ربات)
🦾 This Thursday, we are going to visit Taarlab to witness Reinforcement Learning in action—as applied to the exciting challenge of robotic grasping! It’s a unique opportunity to explore research in practice and get inspired.
New Approaches in Robotic Grasping [Abstract]
🗓 Thursday, April 17 (۲۸ فروردین)
🕛 11 AM to 1 PM
📍 Taarlab Location [Google Map]:
تهران، انتهای امیرآباد شمالی، جنب خوابگاه دخترانه چمران، ساختمان شماره ۳ ژئوفیزیک، اتاق 217B
If you wish to join us please fill out the following form:
🔗 https://forms.gle/BCqiHs1ipMEzMzxP9
⏰ Submission Deadline: Wednesday, Apr 16 (۲۷ فروردین) @ 5:59 PM
⚠️ Seats are limited. Official students of the class will be prioritized.
@DeepRLCourse
🦾 This Thursday, we are going to visit Taarlab to witness Reinforcement Learning in action—as applied to the exciting challenge of robotic grasping! It’s a unique opportunity to explore research in practice and get inspired.
New Approaches in Robotic Grasping [Abstract]
🗓 Thursday, April 17 (۲۸ فروردین)
🕛 11 AM to 1 PM
📍 Taarlab Location [Google Map]:
تهران، انتهای امیرآباد شمالی، جنب خوابگاه دخترانه چمران، ساختمان شماره ۳ ژئوفیزیک، اتاق 217B
If you wish to join us please fill out the following form:
🔗 https://forms.gle/BCqiHs1ipMEzMzxP9
⏰ Submission Deadline: Wednesday, Apr 16 (۲۷ فروردین) @ 5:59 PM
⚠️ Seats are limited. Official students of the class will be prioritized.
@DeepRLCourse
🔥12