"Reinforcement Learning (RL)" is an area of machine learning. The goal here is to enable an autonomous agent to accomplish a task through trial-and-error without using annotated training data. The agent is not given examples of correct actions (e.g., as in Supervised Learning), but must interact with the environment to discover a strategy that maximizes the expected cumulative reward for the task at hand.

Through a combination of theory and actual industry case studies, this two-day seminar will enable you to understand the value and impact of this technology on your business. You will learn how to formulate several problem types according to the RL paradigm and design (or, respectively, select from a large base) efficient algorithms to solve them. In addition, through practical examples, you will gain a solid understanding of how to apply RL algorithms in practice using state-of-the-art software frameworks.

By participating in the seminar, you will: understand the foundations of Reinforcement Learning, learn how to formulate a given problem within the context of Reinforcement Learning paradigm, study different types of Reinforcement Leaning algorithms, implement Reinforcement Learning algorithms for real-world problems using state-of-the-art software, learn how to apply Reinforcement Learning in real-world autonomous systems

Content of the Seminar »Reinforcement Learning«

Day 1

The THEORETICAL basics
Short introduction on AI and Autonomous Systems Markov Decision Processes and Dynamic Programming Q-Learning and SARSA algorithms Value Function Approximation Hands-on examples of basic algorithms

Day 2

Deep Reinforcement learning in practice
Deep Q-Learning algorithms and extensions Policy search algorithms Actor Critic methods

Advanced Topics:

Imitation Learning and Inverse Reinforcement Learning
Model-based Reinforcement Learning
Simulation to Reality transfer
Interpretable Reinforcement Learning
End-to-End Reinforcement Learning

Best Practices:

Reward Shaping and Curriculum-Learning
Hyperparameter-Tuning
Debugging of Reinforcement Learning Algorithms
Selecting suitable algorithms for different types of problems
Hands-on examples for core algorithms
Reinforcement Learning examples in industrial applications

Who should attend this seminars?

Industry managers with strategic decision-making responsibilities
Key members of in-house R&D teams
Algorithm engineers and programmers
Industry consultants

Price: 1200 Euro