Multiagent Systems: Introduction to Noncooperative Game Theory: Games in Normal Form

By Yoav Shoham, Kevin Leyton-Brown. 2008

1,781 citations recorded by the source corpus.

Subfields: Earth-Surface Processes, Game & Decision Theory

How researchers see this paper

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

In Earth-Surface Processes

In Game & Decision Theory

Citations in the corpus

OpenSpiel: A Framework for Reinforcement Learning in Games (2019, background): “Games in OpenSpiel are represented as procedural extensive-form games [52, 63], though in some cases can also be cyclic such as in Markov Decision Processes [67] and Markov games [37].”
Counterfactual Multi-Agent Policy Gradients (2017, methodology): “(2015) use a combination of DQN with independent Q-learning (Tan 1993; Shoham and Leyton-Brown 2009) to learn how to play twoplayer pong.”
Learning to Communicate with Deep Multi-Agent Reinforcement Learning (2016, neutral): “While independent Q-learning can in principle lead to convergence problems (since one agent’s learning makes the environment appear non-stationary to other agents), it has a strong empirical track record [15, 16], and was successfully applied to two-player pong.”
Empirically Evaluating Multiagent Learning Algorithms (2014, methodology): “In each step of the iterative IDR algorithm mixed-strategy domination is checked using a linear program (see, for example, Shoham and Leyton-Brown (2008)).”
The Hanabi Challenge: A New Frontier for AI Research (2019, background): “n [79]. There has been much work that proposes to model beliefs about the intentions or plans of other agents. Several formalisms have been proposed for this, such as I-POMDPs [80] and Bayesian games [81]. However, algorithms to compute exact solutions quickly become intractable for complex problems”
Learning to Communicate to Solve Riddles with Deep Distributed Recurrent Q-Networks (2016, methodology): “While independent Q-learning can in principle lead to convergence problems (since one agent’s learning makes the environment appear non-stationary to other agents), it has a strong empirical track record (Shoham et al., 2007; Shoham & Leyton-Brown, 2009; Zawadzki et al., 2014).”
A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning (2017, background): “Note that finding an equilibrium in a zero-sum game takes time polynomial in |Π|, and is PPAD-complete for general-sum [89].”
The Mechanics of n-Player Differentiable Games (2018, background): “Finding equilibria can be reformulated as a nonlinear complementarity problem, but these are ‘hopelessly impractical to solve’ in general (Shoham & Leyton-Brown, 2008) because the problem is PPAD hard (Daskalakis et al., 2009).”
TarMAC: Targeted Multi-Agent Communication (2018, background): “Multi-agent systems fall at the intersection of game theory, distributed systems, and Artiﬁcial Intelligence in general (Shoham & Leyton-Brown, 2008), and thus have a rich and diverse literature.”
Evaluation of Flexibility Markets for Retailer–DSO–TSO Coordination (2019, methodology): “In a VCG mechanism the pay-off of a buyer is its relative contribution to the total social welfare [21].”
DESIRE: Distant Future Prediction in Dynamic Scenes with Interacting Agents (2017, background): “However, as noted in [38], typically learning in multi-agent setting is inherently more complex than single agent setting [40, 39, 6].”
Predicting human behavior in unrepeated, simultaneous-move games (2013, background): “12 One might wonder whether the -equilibrium solution concept (see e.g. Shoham and Leyton-Brown, 2008, Section 3.4.7) solves either of these problems.”
Indoor navigation by blind people: Behaviors and challenges in unfamiliar spaces and buildings (2019, methodology): “Based on these numbers, the various assistance was ranked using the Borda Scoring Rule (BSR) (Shoham & Leyton-Brown, 2008); see Table 1.”
Advanced Demand Side Management for the Future Smart Grid Using Mechanism Design (2012, methodology): “Here, we will use a popular choice for this function which is referred to as Clarke tax [37],”
Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms (2019, background): “6 In contrast, another framework, named extensive-form games [105, 106], can handily model imperfect information for multi-agent decision-making.”
Handbook of Computational Social Choice (2016, neutral): “Social choice theory is part of the basic repertoire available for modeling the fundamental features of multiagent systems (Wooldridge, 2009; Shoham and Leyton-Brown, 2009).”