Practical Reinforcement Learning
Leverage Reinforcement Learning to solve complex real-world problems.
Dive into RL to control complex systems, optimize decisions, and build advanced AI models that tackle real-world challenges.
- Next Training: To be announced
- Duration: To be announced
- Price: To be announced
- Languages: English (German available upon request)
- Location: Online (Onsite available upon request)
Details
Reinforcement Learning (RL) is an integral part of various algorithms and applications: from controlling robots and complex systems like weather balloons to breakthroughs in games (Go, Chess, Dota, Starcraft) and algorithm development (Matrix Multiplication, Compression, and others). Elements of RL also play crucial roles in the newest developments in large language models, like alignment of models with RL from Human Feedback (RLHF), prompting techniques that use Monte Carlo Tree Search, and reasoning traces in OpenAI’s o1 models.
Despite such successes and the long history of RL, there are comparatively few real-world applications and even fewer mature software resources. Unlike areas like Computer Vision and Natural Language Processing, as of 2024, Reinforcement Learning is far from being commoditized. This training by Oraios is a step towards improving the current situation.
We will discuss which problems are most suitable for RL, and when other techniques should be preferred. Then we go on to building custom environments, highlighting the most common problems and pitfalls in environment design, and demonstrate the structure and the strengths and weaknesses of various RL algorithms. As the developers behind a large open-source RL library (Tianshou) who have also worked on industry applications of RL for multiple years, Oraios’ trainers are uniquely suited for teaching how the challenging techniques behind reinforcement learning can be leveraged for creating real value in applications.
Modules
Understanding RL: Basics, History, and Modern Applications
Understand the foundations of RL, its history, and its applications in the latest AI innovations.
Building RL Environments
Create custom environments and overcome common design challenges to maximize your RL models’ potential.
Algorithm Analysis and Pitfalls
Analyze the strengths, weaknesses, and implementation of key RL algorithms.
Real-World Case Studies
Learn how RL is used to create real value across different sectors and develop skills for practical implementation.
Meet the trainers
Dr. Dominik Jain
Dominik is a computer scientist with a passion for algorithms,
software design and automation in general. As a researcher at
Technische Universität München, he gave courses on the topics of artificial intelligence, knowledge representation, statistical relational models and discrete probability theory. After receiving
his PhD in artificial intelligence in 2012, he spent the next 11 years
working on applied research and development, primarily in the
automotive sector. His work leveraged machine learning,
probabilistic modelling, combinatorial optimisation, search
algorithms, and other methodologies to advance AI-based
capabilities across a diverse array of problem domains. In 2023,
he joined appliedAI’s TransferLab, working on applications of
reinforcement learning and generative AI and developing trainings as well as open-source software for the wider community, before co-founding Oraios AI in September 2024.
Dr. Michael Panchenko
Dr. Dominik Jain
Dominik is a computer scientist with a passion for algorithms,
software design and automation in general. As a researcher at
Technische Universität München, he gave courses on the topics of artificial intelligence, knowledge representation, statistical relational models and discrete probability theory. After receiving
his PhD in artificial intelligence in 2012, he spent the next 11 years
working on applied research and development, primarily in the
automotive sector. His work leveraged machine learning,
probabilistic modelling, combinatorial optimisation, search
algorithms, and other methodologies to advance AI-based
capabilities across a diverse array of problem domains. In 2023,
he joined appliedAI’s TransferLab, working on applications of
reinforcement learning and generative AI and developing trainings as well as open-source software for the wider community, before co-founding Oraios AI in September 2024.
Dr. Michael Panchenko
Get your ticket now!
Contact for inquiries
