Keeping Cool Under Pressure - Reinforcement Learning and Control Workshop
Everyone talks about control, but not everyone means the same thing.
In industrial operations, control determines stability, energy use, emissions, and margin in processes where there is little room for error.
Industrial process operations are energy-intensive by nature, have significant environmental footprints, and operate on tight profitability margins. These systems have long relied on safe and real-time control signals to maintain stability. What is changing now is how reinforcement learning is pushing performance further by layering adaptive intelligence onto existing instrumentation and communication systems to unlock greater gains in efficiency, emissions reduction, and business profitability.
Keeping Cool Under Pressure is a hands-on workshop built to make that shift intuitive. Instead of slides, math, or jargon, you will step into an interactive demo and experience real-time RL and control decisions as they happen. By the end of the session, you will have a feel for what it is like to be an operator managing a live process under pressure.
Agenda
16:30–17:00: Networking
17:00–17:15: Introduction
17:15–18:30: Interactive demo
18:30–19:00: Wrap-up
What to expect
A live, interactive demo simulating real-time RL and control decisions under pressure
A firsthand feel for what it is like to be an operator making split-second control calls
Zero mathematical prerequisites, built for intuition rather than equations
An immersive format that makes advanced process control concepts click quickly
Practical insight into how safe, real-time control signals translate into measurable business value
A perspective that goes beyond PLCs, dashboards, and chatbots
Speaker
Oguzhan Dogru, Ph.D., P.Eng. is an Advanced Process Control leader with nearly a decade of experience driving autonomous control and AI-driven transformation across the oil and energy sectors. He most recently led Support and Advanced Process Control at CruxOCM, where he owned multi-million-dollar program budgets, led enterprise-scale AI initiatives that saved six to seven figures annually, and delivered 40% faster system startups, 50% fewer incidents, and 90% fewer operator interventions through the control frameworks he architected. His Ph.D. in Chemical Engineering from the University of Alberta laid the foundation for his work in reinforcement learning-based process control under sensory uncertainty, and continues to inform his design of adaptive control systems for complex industrial environments.