Traditionally, on the last Friday of each month, the Python community gathered once again for another inspiring Python Belgrade Meetup!

This time, the topic of the evening was “Introduction to Reinforcement Learning with Python”, presented by Oleg Osipov, Senior Data Scientist at X5 Group.

The meetup attracted numerous Python developers, data enthusiasts, and AI lovers eager to discover how machines can learn from interaction and improve their decision-making over time.

Oleg delivered an engaging and practical lecture that demystified the essence of reinforcement learning (RL) — a powerful approach in machine learning where an agent learns by taking actions, observing outcomes, and optimizing its behavior for maximum long-term reward.

He highlighted key RL concepts such as agent, environment, and policy, and explained the challenge of balancing exploration and exploitation, all supported with clear and simple Python code that helped participants grasp the principles instantly.

Particular attention was drawn to real-world business applications of RL — from recommendation systems and resource optimization to supply chains and finance — showing how reinforcement learning is already making a tangible impact.

As always, the evening concluded with a dynamic Lightning Talks session, where community members shared their insights, ideas, and experiences — and, of course, a few good (and bad) jokes over a beer! 

Thanks to everyone who joined us to learn, share, and grow the Python community in Belgrade. See you at the next meetup!

🐍 Tradiocionalno, svakog poslednjeg petka u mesecu, Python zajednica se okupila na još jednom izuzetnom Python Belgrade meetup-u!

Ovog puta, tema večeri bila je „Introduction to Reinforcement Learning with Python“, a predavanje je održao Oleg Osipov, Senior Data Scientist... ⬇️ pic.twitter.com/lkz6W9TRbT

— CDT HUB (@CDTHUB) June 30, 2025