Applied Reinforcement Learning

Reinforcement Learning (RL) is the new frontier in Data Science. It is a very general approach designed to solve sequential decision-making problems applicable to a wide range of business tasks. While RL has already taken over deep learning in number of AI publications, many companies are still not making use of its potential due to lack of data and knowhow. This course will prepare you to address these challenges and get you started on uncovering new innovation opportunities and liberating the potential of the next wave of AI applications.

Apply

Objectives and content

Enquiries and contact

Compare favorites

At a glance

Qualification:

Certificate of attendance "Applied Reinforcement Learning" (2 ECTS)

Start:

on request

Duration:

6 evenings, more details about the implementation

Costs:

CHF 1'150.00

Location:

ZHAW Life Sciences and Facility Management, Zürich, Campus Zentrum, Lagerstrasse 41 (PDF 729,0 KB) and online.

The first and last event will be held on site at ZHAW near HB Zurich (online participation is possible) to get to know each other, form project groups, facilitate networking and celebrate the project outcomes of the participants. Intermediate events will be held online for higher efficiency and convenience.

Language of instruction:

English

Course dates:

Objectives and content

Target audience

Aimed at decision makers and scientific or engineering personnel such as data scientists, software engineers, researchers or research managers who would like to acquire the know-how and skills of state-of-the-art methods to solve decision making problems in order to develop their own RL applications.

Prerequisites for this course: This is an advanced course which assumes you have some programming experience in python and fundamental knowledge of machine learning and deep learning (see our dedicated courses).

Objectives

This course enables the participants to acquire an understanding of the state-of-the-art methods in deep reinforcement learning and the coding skills to start developing RL projects on their own.

The participants will:

Learn what kind of problems can be solved with reinforcement learning
Understand the key concepts of RL solutions
Learn how to build their own RL agents in Python
Get to know a wide range of RL algorithms
Learn how to approach their own RL projects

Content

- Where Reinforcement Learning can help

- Theoretical Foundations of RL

- Basic Algorithms for Decision Making

- Algorithms for Model-Free RL and Model-Based RL

- Creating Simulations and RL Environments

- Practical Aspects of developing RL solutions

Methodology

The course is strongly based on applied exercises. Lectures are split in roughly equal parts of theory and practical programming exercises.

In addition to traditional lectures, the students will experience:

Self-study (preparation and follow-up)
Group work
Parctical programming exercises
A final project where a specific use case is developed end-to-end

More details about the implementation

There are 6 lessons organized once a week on Fridays from 5:30pm to 8pm. The final project presentation will be held during the last lesson.

Enquiries and contact

Dr. Claus Horn

Dr. Claus Horn is the head of the autonomous systems and reinforcement learning group at the institute of computational life sciences at ZHAW. He founded the Reinforcement Learning Zurich community in 2018 to advance the development of RL solutions and enable open education and exchange between professionals working in this field. Before joining ZHAW he worked as a researcher at Stanford University and CERN and has over ten years of experience in building up and leading data science teams in several industries in Switzerland.

Provider

Institute of Computational Life Sciences

Application

General terms and conditions

Conditions

Start	Application deadline	Registration link
on request	on request	Application

go back