This event is the second session of the Reinforcement Learning Talks Series organized by the IEEE Computer Society Türkiye Chapter. Building on the foundational concepts introduced in the first talk, this session will focus on the practical application of reinforcement learning (RL) to real-world problems.
Reinforcement Learning has gained widespread adoption across domains such as robotics, operations research, industrial control, and autonomous systems. This talk will walk participants through classic RL algorithms, demonstrate step-by-step learning workflows, and highlight both the strengths and limitations of current approaches in practical scenarios.
Attendees will gain an understanding of how to frame problems effectively for RL agents, and what it takes to design agents that can learn efficiently through interaction, feedback, and structured exploration.
Topics to be covered include:
-
Problem formulation for real-world RL tasks
-
Overview of classic RL algorithms (e.g., Q-Learning, Policy Gradient)
-
The structure of an RL learning loop in practice
-
Challenges in real-world RL applications and how to address them
-
Design tips for creating effective and robust learning agents
This session is ideal for students, researchers, and practitioners looking to apply reinforcement learning methods in real-world environments or to prepare for more advanced work in AI.