Towards a Better Understanding of Learning with Multiagent Teams

no code implementations • 28 Jun 2023 • David Radke, Kate Larson, Tim Brecht, Kyle Tilbury

While it has long been recognized that a team of individual learning agents can be greater than the sum of its parts, recent work has shown that larger teams are not necessarily more effective than smaller ones.

Learning to Learn Group Alignment: A Self-Tuning Credo Framework with Multiagent Teams

no code implementations • 14 Apr 2023 • David Radke, Kyle Tilbury

Mixed incentives among a population with multiagent teams has been shown to have advantages over a fully cooperative system; however, discovering the best mixture of incentives or team structure is a difficult and dynamic problem.

Hierarchical Reinforcement Learning Meta-Learning

Presenting Multiagent Challenges in Team Sports Analytics

no code implementations • 23 Mar 2023 • David Radke, Alexi Orchard

This paper draws correlations between several challenges and opportunities within the area of team sports analytics and key research areas within multiagent systems (MAS).

Management Sports Analytics

Exploring the Benefits of Teams in Multiagent Learning

no code implementations • 4 May 2022 • David Radke, Kate Larson, Tim Brecht

For problems requiring cooperation, many multiagent systems implement solutions among either individual agents or across an entire population towards a common goal.

Reinforcement Learning (RL)

The Importance of Credo in Multiagent Learning

no code implementations • 15 Apr 2022 • David Radke, Kate Larson, Tim Brecht

We propose a model for multi-objective optimization, a credo, for agents in a system that are configured into multiple groups (i. e., teams).

reinforcement-learning Reinforcement Learning (RL)