How can reinforcement learning agents learn to cooperate and solve problems? In this talk, I will introduce the field of multi-agent reinforcement learning and various approaches that have been taken to address this challenge. I will then introduce our own framework, called Feudal Multi-Agent Hierarchies in which a 'manager' agent learns to communicate sub-goals to multiple, simultaneously-operating 'worker' agents. Finally, I will discuss the future outlook, both of our method and multi-agent reinforcement learning more generally.
YOU MAY ALSO LIKE:
- Leonardo De Marchi's Deep Learning Fundamentals (in London on 22nd - 23rd October 2019)
- Brian Sletten's Data Science with Python Workshop (in London on 18th - 20th November 2019)
- Scala eXchange London 2019 (in London on 12th - 13th December 2019)
- Practical ML 2020 (in London on 2nd - 3rd July 2020)
- Clean Architecture using BLoC & Voyager: DI & the Widget Router (in London on 21st October 2019)
- Security in the Age of Big Data (Data Anonymisation & Encryption) (in London on 21st October 2019)
- How AI can be used to enable assisted living for the ageing population (SkillsCast recorded in October 2019)
- The importance of DataOps (SkillsCast recorded in October 2019)
Feudal Multi-Agent Hierarchies for Cooperative Reinforcement Learning
Sanjeevan Ahilan is a PhD student at the Gatsby Computational Neuroscience Unit working with Peter Dayan. His primary interests are in multi-agent and hierarchical reinforcement learning, and its connections to diverse fields such as neuroscience, psychology and economics. He previously completed a Masters in Neuroscience at UCL (2014) and a undergraduate degree in Natural Sciences at Cambridge University (2013), specialising in Experimental and Theoretical Physics.