Analyzing Complex Strategic Interactions in Multi-Agent Systems

By William E. Walsh, Rajarshi Das, G. Tesauro, Jeffrey O. Kephart. 2002

189 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 Reinforcement Learning

Citations in the corpus

OpenSpiel: A Framework for Reinforcement Learning in Games (2019, background): “Visualization of Evolutionary and Policy Learning Dynamics One common visualization tool in the multiagent learning literature (especially in games) is a phase portrait that shows a vector field and/or trajectories of particle the depict local changes to the policy under specific update dynamics [64”
Multi-agent Reinforcement Learning in Sequential Social Dilemmas (2017, methodology): “This deﬁnition is based on a formalization of empirical game-theoretic analysis [20, 21].”
A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning (2017, background): “Empirical game-theoretic analysis (EGTA) is the study of meta-strategies obtained through simulation in complex games [98, 99].”
A survey and critique of multiagent deep reinforcement learning (2018, background): “The (N)FSP concept was further generalized in Policy-Space Response Oracles (PSRO) [180], where it was shown that fictitious play is one specific meta-strategy distribution over a set of previous (approximate) best responses (summarized by ameta-gameobtained by empirical game theoretic analysis [342”
Evolutionary Dynamics of Multi-Agent Learning: A Survey (2015, background): “the textbooks by Weibull (1997) and Hofbauer and Sigmund (1998) for an introduction.”
An Evolutionary Dynamical Analysis of Multi-Agent Learning in Iterated Games (2005, background): “The evolutionary approach to GT (EGT) [23, 24], in which many of the strong assumptions of classical GT are relaxed, attracts ever more attention of researchers from different fields, such as economics, computer science and artificial intelligence [3, 5, 11, 27, 31, 34, 51].”
What evolutionary game theory tells us about multiagent learning (2007, background): “[28] which assumes that in complex games, boundedly rational buyers and sellers will choose one of a handful of well-established bidding strategies rather than inventing some new approach.”
Actor-Critic Policy Optimization in Partially Observable Multiagent Environments (2018, background): “These analyses are common in multiagent learning as they allow visual depiction of the policy changes and how different factors affect the (convergence) behavior [83, 92, 13, 91, 11, 94, 1, 99, 98, 8, 89].”
A Survey of Learning in Multiagent Environments: Dealing with Non-Stationarity (2017, methodology): “This structure is used in heuristic payoff tables to compress utility representations and corresponding best response mappings (Walsh et al., 2002).”
Choosing Samples to Compute Heuristic-Strategy Nash Equilibrium (2003, methodology): “In contrast, it is p o sible to compute all equilibria within minutes [19].”
α-Rank: Multi-Agent Evaluation by Evolution (2019, methodology): “The purpose of the ﬁrst applications of EGTA was to reduce the complexity of large economic problems in electronic commerce, such as continuous double auctions, supply chain management, market games, and automated trading [6, 7, 71, 72].”
Inequity aversion improves cooperation in intertemporal social dilemmas (2018, methodology): “precisely, we employ a formalization of empirical game theoretic analysis [43, 44].”
A Generalised Method for Empirical Game Theoretic Analysis (2018, unknown): “This symmetry has been the main focus of the use of empirical game theory analysis [7, 9, 14, 16].”
Autocurricula and the Emergence of Innovation from Social Interaction: A Manifesto for Multi-Agent Intelligence Research (2019, methodology): “Empirical game theoretic techniques (Walsh et al., 2002; Wellman, 2006) may be used to analyze behavior in terms of its strategic properties.”