Non-Cooperative Games

By Anton S. Muresan. 2003

6,038 citations recorded by the source corpus.

How researchers see this paper

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

In Game & Decision Theory

Citations in the corpus

Adversarial Example Games (2020, background): “In games, a standard notion of optimality is the concept of Nash equilibrium [56] where each player cannot improve its objective value by unilaterally changing its strategy.”
Generating images with recurrent adversarial networks (2016, background): “The ﬁrst is based on probabilistic generative models, such as the variational autoencoder [11] and a variety of equivalent models introduced at the same time.”
Discovering Diverse Multi-Agent Strategic Behavior via Reward Randomization (2021, background): “In this framework, Nash Equilibrium (NE) (Nash, 1951), where no player could beneﬁt from altering its strategy unilaterally, provides a general solution concept and serves as a goal for policy learning and has attracted increasingly signiﬁcant interests from AI researchers (Heinrich & Silver, 2016;…”
Benchmarking Multi-Agent Deep Reinforcement Learning Algorithms in Cooperative Tasks (2020, background): “These matrix games are challenging due to the existence of local minima in the form of sub-optimal Nash equilibria [Nash, 1951].”
Emergent Communication through Negotiation (2018, methodology): “In this paper, we study communication in the negotiation game (see Figure 1), an established model of non-cooperative games in classical game theory (Nash, 1950b; Neumann & Morgenstern, 1944; Nash, 1950a; 1951; Schelling, 1960; Binmore et al., 1986; Peters, 2008).”
Game Theory in Wireless Networks: A Tutorial (2006, background): “The importance of mixed strategies is further reinforced by the following theorem of Nash [15, 16].”
On difference convexity of locally Lipschitz functions (2011, background): “1 [24] Every such non-cooperative n-person game admits an equilibrium point.”
Jamming Attacks on Remote State Estimation in Cyber-Physical Systems: A Game-Theoretic Approach (2015, background): “Nash defined a mixed strategy Nash Equilibrium for any game with a finite set of strategies and proved that at least one mixed strategy Nash Equilibrium must exist in such a game in [23].”
Using similarity criteria to make issue trade-offs in automated negotiations (2002, methodology): “…which has been shown to implement the Nash bargaining solution under some conditions [46] and thus strengthening the support for the Nash Program [31]) that models the negotiation process as a bi-lateral bargaining game, consisting of an alternating and sequential protocol of offers and…”
Theoretical considerations of potential-based reward shaping for multi-agent systems (2011, background): “The goal of single-agent reinforcement learning is to compute the policy of maximum reward but with multiple agents, potentially competing, the goal becomes Nash Equilibrium [19].”
Pursuit and an evolutionary game (2009, methodology): “A approach dating back to Maynard Smith & Price (1973) and anticipated in the PhD thesis of Nash (1950).”
Machine Learning in the Air (2019, background): “Best Response: A best-response strategy is the optimal one given the strategies of the other agents, i.e., a Nash equilibrium [61].”
Rational Choice Theory and Explanation (2006, background): “Named after John Nash (1951) because in a legendary paper he demonstrated that under a very general set of conditions, the existence of at least one such equilibrium point is guaranteed.”
Modeling Purposeful Adaptive Behavior with the Principle of Maximum Causal Entropy (2010, methodology): “Since a Nash equilibria is guaranteed to exist (Nash, 1951) and a Nash equilibria is a special case of correlated equilibria that is additionally constrained to have independent actions: P(a1:K) = ∏ k P(ak), a correlated equilibria is always similarly guaranteed to exist.”
Robust Decentralized Joint Precoding using Team Deep Neural Network (2018, background): “Most of the approaches in the literature dealing with this problem often aim at best-responses (also called Nash Equilibrium) [21], which in our setting are defined as follows.”
A tutorial on modeling and analysis of dynamic social networks. Part I (2017, neutral): “This distribution was defined in [83] as the unique Nash equilibrium [84] in a special non-cooperative “Pari-Mutuel” game (betting on horse races), which can be found by solving a special optimization problem, referred now to as the Eisenberg-Gale convex program [85].”
On the Complexity of Nash Equilibria and Other Fixed Points (Extended Abstract) (2010, methodology): “Nash proved his theorem in [33] using Brouwer’s theorem: he showed that for every finite game, Γ, the Brouwer fixed points of the following function, FΓ, are the NEs of Γ: FΓ(x)(i,j) .”
The challenge of poker (2002, background): “For example , the earliest investigations in game theory, by luminaries such as John von Neumann and John Nash, used simplified poker to illustrate the fundamental principles [22] [23] [38].”