Jochen Luithardt
I'm the Co-Founder of pi_optimal, where we're working to democratize reinforcement learning and make it usable for real-world decision-making. My passion lies in building AI systems that don't just work in theory, but actually solve meaningful problems in practice.
Before that, I was Lead Data Scientist at Stellwerk3 GmbH, where I led the development of a model-based reinforcement learning project for campaign control. I also had the chance to represent the company at Cyber Valley Incubator events and build a strong, collaborative data team.
My academic journey brought me to the Max Planck Institute for Intelligent Systems, where I focused on challenges in autonomous learning — from sparse rewards in model-free RL to structured world models and graph networks in model-based approaches. Earlier on, I also worked in digital advertising technology at Gruner + Jahr, developing deep learning models for ad click prediction.
Across all these experiences, one thing has stayed the same: I love taking complex machine learning concepts and turning them into impactful, real-world applications.
Session
Reinforcement Learning (RL) has shown superhuman performance in games and is already delivering value in Big Tech. But despite its potential, RL remains largely inaccessible to most developers. Why? Because real-world RL is hard—it demands data, infrastructure, and tools that are often built for researchers, not practitioners.
This talk shares the journey of applying RL to a real-world use case without having a PhD. It’s a story of figuring things out through hands-on experimentation, trial and error, and building what didn’t exist. We’ll explore what makes RL powerful, why it’s still rare in practice, and how you can get started. Along the way, you’ll learn about the key challenges of production RL, how to work around them, and how the open-source toolkit pi_optimal can help bridge the gap. Whether you're just RL-curious or ready to dive in, this talk offers practical insights and a demo to help you take your first steps.