Biasing Coevolutionary Search for Optimal Multiagent Behaviors

By Liviu Panait, Sean Luke, R. Wiegand. 2006

101 citations recorded by the source corpus.

Subfields: Management Science and Operations Research, Safety Research, 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 Management Science and Operations Research

In Safety Research

In Sociology and Political Science

Citations in the corpus

Weighted QMIX: Expanding Monotonic Value Function Factorisation (2020, background): “Algorithms which suffer from relative overgeneralisation [23, 33], or which make poor trade-offs in their representation (as VDN and QMIX do) can fail to solve this task.”
Deep Coordination Graphs (2019, background): “However, that policy may not be learnable due to a game-theoretic pathology called relative overgeneralization (Panait et al., 2006): during exploration other agents act randomly and punishment caused by uncooperative agents may outweigh rewards that would be achievable with coordinated actions.”
Multiagent Soft Q-Learning (2018, methodology): “To show that our Multaigent Soft Q-Learning method can achieve better coordination, we consider the Max of Two Quadractics game from previous literature (Panait, Luke, and Wiegand 2006).”
Large scale evolutionary optimization using cooperative coevolution (2008, background): “In the domain of learning multiagent behaviors, CC represents a natural approach to applying traditional evolutionary computation [7,8].”
Metaheuristics in large-scale global continues optimization: A survey (2015, methodology): “The CC method is applied in a wide range of real-world applications [18,54,133,135,116,8].”
Multilevel cooperative coevolution for large scale optimization (2008, background): “In the domain of learning multiagent behaviors, CC represents a natural approach to applying traditional evolutionary computation [11], [12].”
Probabilistic Recursive Reasoning for Multi-Agent Reinforcement Learning (2019, unknown): “We adopt the same differential game, the Max of Two Quadratic Game, as Panait et al. (2006); Wei et al. (2018).”
Lenient Learning in Independent-Learner Stochastic Cooperative Games (2016, methodology): “This is a heavy revision of the original LMRL algorithm, which was originally meant only for repeated games (Panait et al., 2006b).”
FOP: Factorizing Optimal Joint Policy of Maximum-Entropy Multi-Agent Reinforcement Learning (2021, methodology): “We adopt the differential game, the Max of Two Quadratic (MTQ) Game, from Panait et al. (2007) and Wei et al. (2018).”