Multi-Agent Influence Diagrams for Representing and Solving Games

By Daphne Koller, Brian Milch. International Joint Conference on Artificial Intelligence, 2001

476 citations recorded by the source corpus.

Subfields: Artificial Intelligence, General Decision Sciences, Management Science and Operations Research

View Paper: https://www.semanticscholar.org/paper/b31be41841d83b6e818355aa60a22befac099e0a

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 General Decision Sciences

In Management Science and Operations Research

Citations in the corpus

A decision network account of reasoning about other people's choices. (2015, methodology): “Although decision networks have not been previously explored as psychological models, they have been used by artificial intelligence researchers to create intelligent agents in multi-player games (Gal & Pfeffer, 2008; Koller & Milch, 2003; Suryadi & Gmytrasiewicz, 1999).”
Reasoning about reasoning by nested conditioning: Modeling theory of mind with probabilistic programs (2014, methodology): “For example, the multi-agent influence diagrams proposed by Koller and Milch [18] combine the expressive power of graphical models with the analytical tools of game theory, but their focus is not on representing knowledge that players’ might have about other players’ reasoning.”
Predicting human behavior in unrepeated, simultaneous-move games (2013, background): “…open problem for future work is finding a way to address this computational problem by representing the games compactly (e.g., Kearns et al., 2001; Koller and Milch, 2001; Jiang et al., 2011), such that expected utility can be computed efficiently over even a very large action space. validation:…”
Computing optimal randomized resource allocations for massive security games (2009, methodology): “Our approach is similar in spirit to other compact representations for games [7, 6], but tailored to security domains.”
Context-specific multiagent coordination and planning with factored MDPs (2002, methodology): “This definition is the directed extension of the definition we proposed in previous work [8] and is the collaborative counterpart of the relevance graph proposed for competitive settings by Keller and Milch [11].”
Exploiting Agent and Type Independence in Collaborative Graphical Bayesian Games (2011, background): “On the contrary, it explicitly represents the contributions of each joint type, thereby capturing type independence.”
Graphical Models for Game Theory (2001, background): “Koller and Milch (2001) describe an extension of influence diagrams to representing -player games, and suggest the importance of exploiting graphical structure in solving normal-form games.”
Methods for empirical game-theoretic analysis (extended abstract) (2006, background): “The recent surge in interest among AI researchers in game theory has led to numerous advances in game modeling (Gal & Pfeffer 2004; Kearns, Littman, & Singh 2001; Koller & Milch 2003; Leyton-Brown & Tennenholtz 2003) and solution techniques (Gilpin & Sandholm 2006; Porter, Nudelman, & Shoham 2004)”
A Framework for Sequential Planning in Multi-Agent Settings (2005, background): “Some recent work in AI follows that tradition [5, 14, 17, 18].”
Settable Systems: An Extension of Pearl's Causal Model with Optimization, Equilibrium, and Learning (2009, result): “We relate our results to multi-agent influence diagrams (Koller and Milch, 2003) in Section 6.4.”
Bayesian networks and boundedly rational expectations (2016, background): “…models have been introduced into economics in other contexts: as a way of representing games and facilitating computation of Nash equilibrium (see Kearns, Littman and Singh (2001) and Koller and Milch (2003)), or as a way of discussing causality in econometric models (see White and Chalak (2009)).”