24 April 2024, 12:00 – 13:00 (CET), Online

 

Webinar

 

Distributed and Hierarchical Reinforcement Learning 

 

 

In this webinar, we will provide an overview of two emerging topics in Reinforcement Learning (RL): Distributed RL and Hierarchical RL.

Distributed Reinforcement Learning (DRL) exploits the power of decentralized computation and collaboration. At its core, DRL aims to distribute the learning process across multiple agents, each interacting with its environment, yet collectively contributing to the attainment of a common goal. This approach offers several advantages, including enhanced scalability, improved robustness, and accelerated learning rates, particularly in large-scale and complex environments.

 

In the webinar, for both DRL and HRL, we will provide a general definition of the paradigm, discuss the learning objectives, challenges, and solution concepts. We will also introduce some essential algorithmic solutions, applications, and future research directions, with particular attention to the use cases of the AI4REALNET project.

 

Agenda 

 

• Introduction
• Distributed Reinforcement Learning
• Hierarchical Reinforcement Learning
• Q&A

 

Missed this event?

Watch it HERE.

 

Download the slides below:

Slides