Zobrazeno 1 - 10
of 146
pro vyhledávání: '"Kagan Tumer"'
Publikováno v:
Proceedings of the Genetic and Evolutionary Computation Conference Companion.
Autor:
Gaurav Dixit, Kagan Tumer
Publikováno v:
Proceedings of the Genetic and Evolutionary Computation Conference Companion.
Autor:
Golden Rockefeller, Kagan Tumer
Publikováno v:
Proceedings of the Genetic and Evolutionary Computation Conference Companion.
Publikováno v:
Proceedings of the Genetic and Evolutionary Computation Conference.
Autor:
Joshua Cook, Kagan Tumer
Publikováno v:
Proceedings of the Genetic and Evolutionary Computation Conference.
Publikováno v:
2021 International Symposium on Multi-Robot and Multi-Agent Systems (MRS).
Autor:
Kagan Tumer, Joshua Cook
Publikováno v:
GECCO Companion
Cooperative Co-evolutionary Algorithms effectively train policies in multiagent systems with a single, statically defined team. However, many real-world problems, such as search and rescue, require agents to operate in multiple teams. When the struct
Publikováno v:
GECCO Companion
Many long term robot exploration domains have sparse fitness functions that make it hard for agents to learn and adapt. This work introduces Adaptive Multi-Fitness Learning (A-MFL), which augments the structure of Multi-Fitness Learning (MFL) [7] by
Publikováno v:
GECCO Companion
In many real-world multiagent systems, agents must learn diverse tasks and coordinate with other agents. This paper introduces a method to allow heterogeneous agents to specialize and only learn complementary divergent behaviors needed for coordinati
Publikováno v:
GECCO
Evolving effective coordination strategies in tightly coupled multi-agent settings with sparse team fitness evaluations is challenging. It relies on multiple agents simultaneously stumbling upon the goal state to generate a learnable feedback signal.