Evolutionary game theory and multi-agent reinforcement learning

By Karl Tuyls, Ann Nowé. 2005

137 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Management Science and Operations Research

How researchers see this paper

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

In Artificial Intelligence

In Management Science and Operations Research

Citations in the corpus

Lenient Multi-Agent Deep Reinforcement Learning (2017, background): “ement learning agents [2,21,16] which should not come as a surprise given that both reinforcement learning and evolutionary algorithms converge towards replicator dynamics of evolutionary game theory [22,16,23]. Lenient learners are more likely to converge towards an optimal policy due to forgiving ”
Multiagent Learning: Basics, Challenges, and Prospects (2012, background): “For an elaborate discussion on these concepts we refer to Busoniu, Babuska, and De Schutter (2008); Tuyls and Nowe (2005); Weibull (1996); and Vega-Redondo (2003).”
Independent reinforcement learners in cooperative Markov games: a survey regarding coordination problems (2012, background): “Various RL algorithms have been proposed in the literature for ILs and fully-cooperative MAS.”
A Comprehensive Survey of Multiagent Reinforcement Learning (2008, unknown): “Tuyls and Now·e [28] investigate the relationship between MARL and evolutionary game theory in more detail, focusing on static tasks.”
An Overview of Cooperative and Competitive Multiagent Learning (2005, background): “For the connection between these concepts we refer the interested reader to [175, 133, 187].”
Reaching pareto-optimality in prisoner’s dilemma using conditional joint action learning (2007, background): “Though Vidal and Durfee explicitly models the influence of a player’sactiononotherstheircalculationsrequiremoreinformationthanweassumeis available[30].Foramorecompletelistofmultiagentreinforcementlearningresearch, refer to recent surveys of the literature[21; 28 ].”
Game Theory in Wireless and Communication Networks (2008, background): “, Q-learning) of agents can be modeled as an evolutionary game [481].”
Game Theory and Multi-agent Reinforcement Learning (2012, background): “In a related branch of research (Tuyls and Nowé, 2005; Wunder et al, 2010) the dynamics of independent Q-learning are studied using techniques from evolutionary game theory (Smith, 1982).”
Multi-agent Reinforcement Learning: An Overview (2010, background): “Tuyls and Now´e [132] have investigated the relationship between MARL and evolutionary game theory, focusing on static tasks.”
Emerging social awareness: Exploring intrinsic motivation in multiagent learning (2011, background): “It may also be interesting to further explore the relation between our work and evolutionary game theory, exploring the relation between this discipline and reinforcement learning [24].”
Emergence of Norms through Social Learning (2007, background): “In our formulation, norms evolve as agents learn from their interactions with other agents in the society using multiagent reinforcement learning algorithms [ Panait and Luke, 2005; Tuyls and Now´e, 2006 ] .”
From Poincaré Recurrence to Convergence in Imperfect Information Games: Finding Equilibrium via Regularization (2020, background): “…regularization of Q-learning in matrix games can induce the policy to converge in real-time to a Nash equilibrium (Tuyls et al., 2003; Kaisers & Tuyls, 2010; 2011) or in the replicator dynamics to Quantal-Response-Equilibrium (Ortega & Legg, 2018; McKelvey & Palfrey, 1995; Tuyls & Nowé, 2005).”
Autocurricula and the Emergence of Innovation from Social Interaction: A Manifesto for Multi-Agent Intelligence Research (2019, background): “Consider a game with intransitive strategic dynamics like rock-paper-scissors (Singh et al., 2000; Tuyls and Nowé, 2005).”