📢 Anonymous Feedback Form
Got concerns or suggestions about the course?
Share them anytime—completely anonymously! The form will stay open until the end of the course, and we'll reflect on all feedback and take action whenever possible.
🔗 https://forms.gle/snzciPzEbJo698GE8
You can always find it in the channel info for easy access.
Your voice matters! 🚀
Got concerns or suggestions about the course?
Share them anytime—completely anonymously! The form will stay open until the end of the course, and we'll reflect on all feedback and take action whenever possible.
🔗 https://forms.gle/snzciPzEbJo698GE8
You can always find it in the channel info for easy access.
Your voice matters! 🚀
Google Docs
📢 Anonymous Feedback!
Your thoughts matter! 🧠💡 This is your chance to share honest and anonymous feedback about the course. Your insights help us improve and create a better learning experience for everyone! 🚀🎯
All responses are completely anonymous—so feel free to be open and…
All responses are completely anonymous—so feel free to be open and…
❤3👎1
📣 Final Video of Lecture 3 is Out!
🎥 https://www.youtube.com/watch?v=otAnod9-J0E
🎥 https://www.youtube.com/watch?v=otAnod9-J0E
YouTube
Lecture 3 | Value-Based Methods | Spring 25
Welcome to the 3rd lecture of our Spring 2025 Deep RL Course! 🚀
In this session, we dive into the value-based methods 🤖
💡 Want more resources?
Get the slides and extra goodies here:
🔗 https://deeprlcourse.github.io/lectures/week2
Stay Connected:
✉️ d…
In this session, we dive into the value-based methods 🤖
💡 Want more resources?
Get the slides and extra goodies here:
🔗 https://deeprlcourse.github.io/lectures/week2
Stay Connected:
✉️ d…
🔥1
📣 Final Video of Lecture 4 is Out!
🎥 https://www.youtube.com/watch?v=7MrSo-I0p4U
🎥 https://www.youtube.com/watch?v=7MrSo-I0p4U
YouTube
Lecture 4 | Value-Based Methods | Spring 25
Welcome to the 4th lecture of our Spring 2025 Deep RL Course! 🚀
In this session, we continue to dive into the value-based methods 🤖
💡 Want more resources?
Get the slides and extra goodies here:
🔗 https://deeprlcourse.github.io/lectures/week2
Stay Connected:…
In this session, we continue to dive into the value-based methods 🤖
💡 Want more resources?
Get the slides and extra goodies here:
🔗 https://deeprlcourse.github.io/lectures/week2
Stay Connected:…
🔥3👍1
📣 Workshop material for Week 2 is available here:
🔗 https://github.com/DeepRLCourse/Workshop-2-Material
🔗 https://github.com/DeepRLCourse/Workshop-2-Material
GitHub
GitHub - DeepRLCourse/Workshop-2-Material
Contribute to DeepRLCourse/Workshop-2-Material development by creating an account on GitHub.
📣 Important Announcement
You can submit your solutions for Homework 2 and Homework 3 together on March 2 (۱۲ اسفند).
You can submit your solutions for Homework 2 and Homework 3 together on March 2 (۱۲ اسفند).
❤16
🚀 We will be live from 2:50 PM. Join us here:
https://www.youtube.com/@DeepRLCourse
🎙 Title: From Shortest Paths to Value Iteration to Q-Learning
👨🏫 Speaker: Chris Watkins (Professor of Computer Science, Royal Holloway)
https://www.youtube.com/@DeepRLCourse
🎙 Title: From Shortest Paths to Value Iteration to Q-Learning
👨🏫 Speaker: Chris Watkins (Professor of Computer Science, Royal Holloway)
👍1
🚀 We will be live from 5:20 PM. Join us here:
https://www.youtube.com/@DeepRLCourse
🎙 Title: Assessing the Robustness of Deep RL Algorithms
👨🏫 Speaker: Michael L. Littman (Brown University, Humanity-Centered Robotics Initiative)
https://www.youtube.com/@DeepRLCourse
🎙 Title: Assessing the Robustness of Deep RL Algorithms
👨🏫 Speaker: Michael L. Littman (Brown University, Humanity-Centered Robotics Initiative)
👍2
Lecture_4_Summary.pdf
389.3 KB
🎓 Summary of Lecture 4 📚
🔗 Quiz Link: https://forms.gle/AeiroVwcK7K5AKMNA
🕐 Deadline: 1:30 PM (before the class)
Stay on track and get it done! 🚀
🔗 Quiz Link: https://forms.gle/AeiroVwcK7K5AKMNA
🕐 Deadline: 1:30 PM (before the class)
Stay on track and get it done! 🚀
📣 Website Updated with Last Week’s Material!
Don't forget to take a look at the slides for today's lecture before the class:
🔗 https://deeprlcourse.github.io/lectures/week3/#lecture-5
Stay on track and keep learning! 🚀📚
Don't forget to take a look at the slides for today's lecture before the class:
🔗 https://deeprlcourse.github.io/lectures/week3/#lecture-5
Stay on track and keep learning! 🚀📚
deeprlcourse.github.io
Week 3: Policy-Based Methods - Deep RL Course
This page contains the lecture materials for Week 3 of the Deep Reinforcement Learning course, including video recordings, slides, and summaries.
👍1
📣 Feedback Form for Summary & Quizzes of Lecture 1 to 4
🌐 https://forms.gle/n3FiZzQjyeSKTEo88
⏰ Deadline: Mar 2, 12 Midnight
🌐 https://forms.gle/n3FiZzQjyeSKTEo88
⏰ Deadline: Mar 2, 12 Midnight
📣 Screen record of Lecture 5 is Out!
🎥 https://www.youtube.com/watch?v=6V26_jje_ZE
🎥 https://www.youtube.com/watch?v=6V26_jje_ZE
YouTube
Lecture 5 | Policy-Based Methods | Spring 25 (Screen Record)
Welcome to the 5th lecture of our Spring 2025 Deep RL Course! 🚀
In this session, we dive into the policy-based methods 🤖
💡 Want more resources?
Get the slides and extra goodies here:
🔗 https://deeprlcourse.github.io/lectures/week3
Stay Connected:
✉️ …
In this session, we dive into the policy-based methods 🤖
💡 Want more resources?
Get the slides and extra goodies here:
🔗 https://deeprlcourse.github.io/lectures/week3
Stay Connected:
✉️ …
🔥2
📣 Course Notes for <Week 2: Value-based Methods> are Out!
🌐 https://deeprlcourse.github.io/course_notes/value-based
🌐 https://deeprlcourse.github.io/course_notes/value-based
deeprlcourse.github.io
Week 2: Value-based Methods - Deep RL Course
This page delves into the foundational concepts and methods of value-based reinforcement learning. It covers the Bellman equations, dynamic programming techniques like value iteration and policy iteration, Monte Carlo methods for prediction and control, and…
📣 Important Announcement
Today's lecture (۷ اسفند) will be held online at 1:30 PM. Please join us via the following link:
🌐 https://vc.sharif.edu/ch/rohban
Today's lecture (۷ اسفند) will be held online at 1:30 PM. Please join us via the following link:
🌐 https://vc.sharif.edu/ch/rohban
🫡4💯1
Lecture_5_Summary.pdf
2.2 MB
🎓 Summary of Lecture 5 📚
🔗 Quiz Link: https://forms.gle/x1c8USwQ3ujhgzJv5
🕐 Deadline: 1:30 PM (before the class)
Stay on track and get it done! 🚀
🔗 Quiz Link: https://forms.gle/x1c8USwQ3ujhgzJv5
🕐 Deadline: 1:30 PM (before the class)
Stay on track and get it done! 🚀
❤4
🚀 Join Peter Stone’s Talk at Sharif University of Technology
🎙 Title: Multiagent RL: Cooperation and Competition
👨🏫 Speaker: Peter Stone (Professor of Computer Science, University of Texas at Austin)
📅 Date: Thursday (Feb 27, 2025)
🕗 Time: 3:30 PM Iran Time
💡 Sign Up Here: https://forms.gle/M4QxTUWimGyvUmPv7
@DeepRLCourse
🎙 Title: Multiagent RL: Cooperation and Competition
👨🏫 Speaker: Peter Stone (Professor of Computer Science, University of Texas at Austin)
📅 Date: Thursday (Feb 27, 2025)
🕗 Time: 3:30 PM Iran Time
💡 Sign Up Here: https://forms.gle/M4QxTUWimGyvUmPv7
@DeepRLCourse
💯6
🚀 Professor Peter Stone recommends that all of you watch his talk at RLC 2024, noscriptd: "Practical Reinforcement Learning: Lessons from 30 Years of Research"
🎥 https://www.youtube.com/watch?v=5Dw4OoJK9Qw
🎥 https://www.youtube.com/watch?v=5Dw4OoJK9Qw
YouTube
Peter Stone - Practical Reinforcement Learning: Lessons from 30 Years of Research - RLC 2024
Edited by Gor Baghdasaryan
❤2
PeterStoneTalk.pdf
201.1 KB
🚀 Professor Peter Stone also invites all of you to join his latest talk online on Zoom, noscriptd: "Outracing Champion Gran Turismo Drivers with Deep Reinforcement Learning"
📅 Date: Wednesday (Feb 26, 2025)
🕗 Time: 1:00 AM Iran Time
🔗 https://texastech.zoom.us/my/stas.tiomkin
🆔 Meeting ID: 554 589 4586
🔒 Passcode: 12345
📅 Date: Wednesday (Feb 26, 2025)
🕗 Time: 1:00 AM Iran Time
🔗 https://texastech.zoom.us/my/stas.tiomkin
🆔 Meeting ID: 554 589 4586
🔒 Passcode: 12345
🔥1
📣 SeyyedAli MirGhasemi, one of the designers of Homework 3, explains the homework for you:
🎥 https://www.youtube.com/watch?v=6Nbc6GYld7U
🎥 https://www.youtube.com/watch?v=6Nbc6GYld7U
YouTube
Homework 3 | Policy-Based Methods | Spring 25
Presented by SeyyedAli MirGhasemi
🔗 https://www.linkedin.com/in/sayyed-ali-mirghasemi-6033661b9
📂 Access the Homework:
🔗 https://deeprlcourse.github.io/homeworks/week3
Stay Connected:
✉️ deeprlcourse@gmail.com
🌐 https://deeprlcourse.github.io
📺 https:/…
🔗 https://www.linkedin.com/in/sayyed-ali-mirghasemi-6033661b9
📂 Access the Homework:
🔗 https://deeprlcourse.github.io/homeworks/week3
Stay Connected:
✉️ deeprlcourse@gmail.com
🌐 https://deeprlcourse.github.io
📺 https:/…