A Survey of Collectives

By Kagan Tumer, David Hilton Wolpert. 2004

78 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Mechanical Engineering, Sociology and Political Science

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

1. Adrian K. Agogino
2. Ana Lúcia Cetertich Bazzan
3. Kagan Tumer
4. Karl Tuyls

In Mechanical Engineering

1. Adrian K. Agogino
2. Ana Lúcia Cetertich Bazzan
3. Kagan Tumer
4. Karl Tuyls

In Sociology and Political Science

1. Adrian K. Agogino
2. Ana Lúcia Cetertich Bazzan
3. Kagan Tumer
4. Karl Tuyls
5. Wojciech M. Czarnecki
6. Thore Graepel
7. Joel Z. Leibo
8. Marc Lanctot

Citations in the corpus

• Value-Decomposition Networks For Cooperative Multi-Agent Learning (2017, background): “Other work addressing team rewards in cooperative settings is based on difference rewards (Tumer and Wolpert, 2004), measuring the impact of an agent’s action on the full system reward.”
• Analyzing and visualizing multiagent rewards in dynamic and stochastic domains (2008, methodology): “Indeed, the reward design framework used in this paper has been applied to many domains, including data routing over a telecommunication network [29], multiagent gridworld [26], congestion games (traffic toll lanes) [27, 28, 31] and optimization problems such as bin packing [32] and faulty device se”
• Value-Decomposition Networks For Cooperative Multi-Agent Learning Based On Team Reward (2018, background): “Difference rewards [24] measures the impact of an agent’s action on the team reward, but comes with practical difficulties [1, 6, 18].”
• Opportunities for multiagent systems and multiagent reinforcement learning in traffic control (2009, background): “Tumer and Wolpert [80] for instance have shown that there is no general approach to deal with the complex question of collectives.”