COOKIES: By using this website you agree that we can place Google Analytics Cookies on your device for performance monitoring. |
University of Cambridge > Talks.cam > Artificial Intelligence Research Group Talks (Computer Laboratory) > Controlling Behavioral Diversity in Multi-Agent Reinforcement Learning
Controlling Behavioral Diversity in Multi-Agent Reinforcement LearningAdd to your list(s) Download to your calendar using vCal
If you have a question about this talk, please contact Mateja Jamnik. Diversity has been shown to be key to collective intelligence in natural systems. Despite this, current Multi-Agent Reinforcement Learning (MARL) approaches enforce behavioral homogeneity (to boost efficiency) or blindly promote behavioral diversity via intrinsic rewards or additional loss functions, effectively changing the learning objective and lacking a principled measure for it. In this context, the present work deals with the question of how to control the diversity of a multi-agent system. We introduce Diversity Control (DiCo), a method able to control diversity to an exact value of a given metric by representing policies as the sum of a parameter-shared component and dynamically scaled per-agent components. By applying constraints directly to the policy architecture, DiCo leaves the learning objective unchanged, enabling its applicability to any actor-critic MARL algorithm. We theoretically prove that DiCo achieves the desired diversity, and we provide several experiments, both in cooperative and competitive tasks, that show how DiCo can be employed as a novel paradigm to increase performance and sample efficiency in MARL , as well as lead to the emergence of novel diverse policies. Multimedia results are available on the project’s website. This talk is part of the Artificial Intelligence Research Group Talks (Computer Laboratory) series. This talk is included in these lists:
Note that ex-directory lists are not shown. |
Other listsBlack in Geography student led talks se456's list Robin IrvineOther talksNPA Hierarchy for Quantum Isomorphism and Homomorphism Indistinguishability Networks in action: the crucial role of dynamics in networks neuroscience Ethicronics: From West Cambridge to Market Square: An upgrade for software answering hardware (security) challenges? Impacting Medicine with Microfluidics & Nanotechnology: Advancing Diagnostics and Medicine Enlightenment Scepticism and the Conditions for Political Stability |