07: What Is Reinforcement Learning? With Simon Hirländer

If you want to learn about AI, preorder Romy & Roby and The Secret of Sleep and join Dr. Anastassia Lauterbach on Patreon.In this episode of AI Snacks with Romy & Roby, Dr. Anastassia Lauterbach is joined by AI expert Simon Hirländer from the Intelligent Data Analytics (IDA) Lab at the University of Salzburg. Dive into the fascinating world of reinforcement learning, where Roby the robot learns to move by emulating Romy the cat. Simon shares his vision for the future of AI, emphasizing better communication, political support, and proactive global engagement. Discover insights into machine learning, deep learning advancements, and the impact of AI in gaming. Simon is currently building a Reinforcement Learning Team at PLUS University in Salzburg. Applications range from theoretical aspects - basic research - to real-world applications in local industry. Simon’s team focuses on different flavours of reinforcement learning on multivariate time series and analytics, Bayesian methods, control theory and physics.Before working at the University of Salzburg, Simon worked at CERN in Geneva, Switzerland for several years, during this time period he obtained his PhD. Once again Simon is currently a visiting scientist at CERN, continuing his research.Key Topics Discussed:The need for better AI communicationDemocratizing AI knowledge with Romy and RobyDifferences between the human brain and machinesFuture intelligent system modularityBreakthroughs in reinforcement learning and gamingTimestamps:06:31 AI and deep learning's progress explained.13:16 Simplicity and adaptability are key to future systems.17:22 How behavioural psychology and early computer science led to reinforcement learning.18:39 Machine learning involves temporal difference learning.27:44 Algorithm's limitations in recognizing unfamiliar data.31:07 Modeling vs. data-driven approach for intelligence.32:57 The need for better communication between AI researchers and society.35:31 AI mimics intelligence and may complement human intelligence.39:49 Romy & Roby: Roby learns to walk like Romy.Guest Socials:Simon Hirländer | WebsiteSimon Hirländer | LinkedInSimon Hirländer's TEDx Salzburg | YoutubeSmart Analytics & Reinforcement Learning | WebsitePLUS University of Salzburg, Simon Hirländer | Website