Workshop / Reinforcement Learning: Basics
- Date
- February 23, 2026
- Time
- 12:00 p.m. - 1:00 p.m. ET
- Location
- Eric Palin Hall, 87 Gerrard St. East / Room: EPH207
- Open To
- TMU students and faculty members
- Contact
- Mohamad Shahab mshahab@torontomu.ca, Farrokh Janabi-Sharifi fsharifi@torontomu.ca
The TMU Robotics Council invites you to the following workshop: Reinforcement Learning: Basics with speaker, Dr. Hossein Hassani.
About the workshop
Reinforcement Learning (RL) is the driving force behind some of today’s most exciting AI breakthroughs, from beating world champions at Go to training autonomous robots. In this hands-on workshop, participants will step into the world of AI agents and dynamic environments. We will discuss the core theory behind RL, and explain how agents learn optimal strategies through trial and error. Moving from theory to practice, students will explore tools such as OpenAI Gym to simulate complex environments. Participants will utilize Python tools to implement the Q-learning algorithm. We will then demonstrate concrete examples of how to deploy these Q-learning agents within the OpenAI Gym framework.
Key takeaways
- Understanding Agents, Environments, Rewards, and States.
- Hands-on experience with the OpenAI Gym interface.
- Implementing and tuning a Q-Learning algorithm.
Agenda
- 40-minute lecture on RL, its applications, and python implementation of Q-learning
- 10-minute Q&A session
- In the last 10 minutes, a problem will be presented to participants, which requires them to program an RL agent to perform a task using the OpenAI Gym environment.
Certificate of Completion
Registered participants will work on the presented problem offline and submit their solutions by email to the workshop presenter no later than two weeks after the workshop. Solutions will be evaluated and a badge/certificate of completion will be received only by registered participants who solved the problem.
About the speaker
A subject matter expert in embodied artificial intelligence (AI), Dr. Hossein Hassani investigates how to responsibly and sustainably integrate AI with physical systems.
While many high-performance AI models exist today, they rely on energy-intensive hardware – creating barriers for users and applications. Inspired to make cutting-edge technologies more accessible, Dr. Hassani develops small yet powerful AI models for broader adoption. Throughout his research career, Dr. Hassani has specialized in deep reinforcement learning, computer vision, and large language models. At TMU, he leads an automotive mechatronics research group, applying algorithmic systems to autonomous vehicles and related technologies. His latest research is focused on developing vision-language-action (VLA) models to enable end-to-end autonomous driving, while prioritizing safety and reliability.