Schedule: Reinforcement Learning sessions

Machine learning (ML) and deep learning (DL) projects are becoming increasingly common at enterprises and startups alike and have been a key innovation engine for Amazon businesses such as Go, Alexa, and Robotics. Wenming Ye, Miro Enev, and Mahendra Bairag detail a practical next step in DL learning with instructions, demos, and hands-on labs. Read more.

Whether you're a scientist wanting to test a problem without building costly real-world rigs, a self-driving car engineer wanting to test AI logic in a virtual world, or a data scientist needing to solve a thorny real-world problem without a production environment, Paris Buttfield-Addison, Tim Nugent, and Mars Geldard teach you how to use solution-driven ML AI problem solving with a game engine. Read more.

Building AI applications is hard, and building the next generation of AI applications, such as online and reinforcement learning (RL), is more challenging. Robert Nishihara, Philipp Moritz, and Ion Stoica lead a deep dive into Ray—a general-purpose framework for programming your cluster—its API, and system architecture and examine application examples, including state-of-the-art algorithms. Read more.

Statistical manufacturing has remained largely unchanged since postwar Japan. AI and DL allow for nonlinear feedback and feed-forward systems to be integrated for real-time monitoring and evolution of each part assembly. Vadim Pinskiy explores a system capable of detecting, classifying, and automatically correcting for manufacturing defects in a multinodal process. Read more.

Machine learning has enabled the move from manually programming robots to allowing machines to learn from and adapt to changes in the environment. Bastiane Huang examines how AI-enabled robots are used in warehouse automation, including recent progress in deep reinforcement learning, imitation learning, and real-world requirements for various industrial problems. Read more.

Tremendous progress has been made in applying machine learning to autonomous driving. Li Erran Li explores recent advances in applying machine learning to solving the perception, prediction, planning, and control problems of autonomous driving as well as some key research challenges. Read more.

Cell shaping is used to configure radio antenna parameters to improve the service quality. Julien Forgeat explores a reinforcement learning (RL) approach to configuring radio antenna parameters using industry-leading radio simulators from Ericsson and UC Berkeley RISELab's Ray distributed compute framework together with its built-in RL algorithm in RLlib. Read more.

This year, Unity introduced Obstacle Tower, a procedurally generated game environment designed to test the capabilities of AI-trained agents. Then, they invited the public to try to solve the challenge. Danny Lange reveals what Unity learned from the contest and the real-world impact of observing the behaviors of multiple AI agents in a simulated virtual environment. Read more.

Beyond computer games and neural architecture search, practical applications of deep reinforcement learning (DRL) to improve classical classification or detection tasks are few and far between. Vijay Gabale outlines a technique and some experiences of applying DRL on improving the distribution input datasets to achieve state-of-the-art performance, specifically on object-detection tasks. Read more.

Increased complexity and business demands continue to make enterprise network operation more challenging. Jisheng Wang outlines the architecture of the first autonomous network operation solution along with two examples of ML-driven automated actions. He also details some of his experiences and the lessons he learned applying ML, DL, and AI to the development of SaaS-based enterprise solutions. Read more.

Whether you're a scientist wanting to test a problem without building costly real-world rigs, a self-driving car engineer wanting to test AI logic in a constrained virtual world, or a data scientist needing to solve a thorny real-world problem without a production environment, Paris Buttfield-Addison, Mars Geldard, and Tim Nugent teach you how to use AI problem-solving using game engines. Read more.