Reinforce Learning can be a game changer when you do not have training data, but are instead able to simulate an environment. Unfortunately, the theory of Reinforcement Learning is complex and the vast number of algorithms in that area adds to the burden for getting started. Easyagents takes some of the burden by making it a one-liner to run a Reinforcement Learning algorithm on your problem.

Modeling is easyproductizing models, less so. Distributed training? Forget about it. Say hello to Kubeflow with Holden Karaua system that makes it easy for data scientists to containerize their models to train and serve on Kubernetes.

ML has been advancing rapidly, but only a few contributors focus on the infrastructure and scaling challenges that come with it. Jonathan Peck explores why ML is a natural fit for serverless computing, a general architecture for scalable ML, and common issues when implementing on-demand scaling over GPU clusters, providing general solutions and a vision for the future of cloud-based ML.

Hosting models and productionizing them is a pain point. ML models used for real-time processing require data scientists to have a defined workflow giving them the agility to do self-service seamless deployments to production. Niraj Tank and Sumit Daryani detail open source technologies for building a generic service-based approach for servicing ML decisioning and achieving operational excellence.

Twitter is a large company with many ML use cases. Historically, there have been many ways to productionize ML at Twitter. Yi Zhuang and Nicholas Leonard describe the setup and benefits of a unified ML platform for production and explain how the Twitter Cortex team brings together users of various ML tools.

Machine learning is typically viewed as simply training a model on data. However, the last mile of deploying models to production systems is often overlooked and yet is one of the most critical aspe …