Using Reinforcement Learning in Large Scale Automation at Netflix

Explore the application of reinforcement learning in large-scale automation through this 30-minute conference talk from the Toronto Machine Learning Series (TMLS). Join Stan Kirdey, Senior Distributed Systems Engineer in Insights Engineering at Netflix, as he provides an overview of self-service reinforcement learning tools designed to optimize automation task schedules and reduce failure detection time in software, hardware, and cloud infrastructure. Discover how an agent learns the optimal execution order of automation tasks to either fail fast or identify failure clusters. Gain valuable insights from the speaker's experience in writing and deploying applied reinforcement learning services at Netflix, and learn about the practical implications of this technology in improving efficiency and reliability in large-scale systems.

Using Reinforcement Learning in Large Scale Automation