Reinforcement Learning with TF-Agents & TensorFlow 2.0: Hands On

Abstract: In this workshop you will discover how machines can learn complex behaviors and anticipatory actions. Using this approach autonomous helicopters fly aerobatic maneuvers and even the GO world champion was beaten with it. A training dataset containing the “right” answers is not needed, nor is “hard-coded” knowledge. The approach is called “reinforcement learning” and is almost magical.

Using TF-Agents on top of TensorFlow 2.0 we will see how a real-life problem can be turned into a reinforcement learning task. In an accompanying Python notebook, we implement - step by step - all solution elements, highlight the design of Google’s newest reinforcement learning library, point out the role of neural networks and look at optimization opportunities.

The Python notebooks are hosted on Colab. All you need is a laptop with a current Chrome browser and a Google account. We also gladly discuss application ideas you - as an attendee - might bring along.

Prerequisites
Basic knowledge in software engineering. The implementation is done using TensorFlow 2.0, TF-Agents and Python. Prior knowledge of these is not mandatory.

Technical requirements
Notebook with a recent Chrome browser and a Google account.

Goals
• Basics of reinforcement learning
• When and when not to use it
• Design of TF-Agents on top of TensorFlow 2.0
• Hands-on Implementation

Bio: Christian is a consultant at bSquare with a focus on machine learning & .net development. He has a PhD in computer algebra from ETH Zurich and did a postdoc at UC Berkeley where he researched online data mining algorithms. Currently he applies reinforcement learning to industrial hydraulics simulations.