Hierarchical Reinforcement Learning is a term from the fields of Artificial Intelligence, Automation, and Industry 4.0. It describes a special technique in machine learning that employs a step-by-step, phased approach to problem-solving.
Imagine a robot is to perform a complex task, such as setting a table. Instead of learning everything at once, the main task „setting the table“ is broken down into smaller sub-tasks, such as „placing the plates“, „arranging the cutlery“, and „setting out the glasses“. For each of these sub-tasks, the robot can go through its own small learning processes and find solutions. In the end, the individual results are combined to form the overall solution.
The advantage of Hierarchical Reinforcement Learning is that it breaks down large, complex tasks into manageable sections for machines and AI systems. This allows them to learn faster, be more flexible, and transfer their knowledge more easily to other problems. This method is particularly interesting for industry because it makes machines more efficient and autonomous.
Deutsch 
English (UK)