Equilibrium Refinements for Multi-Agent Influence Diagrams: Theory and Practice

Multi-agent influence diagrams (MAIDs) are a popular form of graphical model that, for certain classes of games, have been shown to offer key complexity and explainability advantages over traditional extensive form game (EFG) representations. In this paper, we extend previous work on MAIDs by introducing the concept of a MAID subgame, as well as subgame perfect and trembling hand perfect equilibrium refinements. We then prove several equivalence results between MAIDs and EFGs. Finally, we describe an open source implementation for reasoning about MAIDs and computing their equilibria.

[1]  Aric Hagberg,et al.  Exploring Network Structure, Dynamics, and Function using NetworkX , 2008, Proceedings of the Python in Science Conference.

[2]  Judea Pearl,et al.  Probabilistic reasoning in intelligent systems - networks of plausible inference , 1991, Morgan Kaufmann series in representation and reasoning.

[3]  Daphne Koller,et al.  Ignorable Information in Multi-Agent Scenarios , 2008 .

[4]  Ramana Kumar,et al.  Modeling AGI Safety Frameworks with Causal Influence Diagrams , 2019, AISafety@IJCAI.

[5]  Halbert White,et al.  Settable Systems: An Extension of Pearl's Causal Model with Optimization, Equilibrium, and Learning , 2009, J. Mach. Learn. Res..

[6]  R. Selten.  Reexamination of the perfectness concept for equilibrium points in extensive games , 1975, Classics in Game Theory.

[7]  Dimitrios Antos,et al.  Identifying reasoning patterns in games , 2008, UAI.

[8]  Marcus Hutter,et al.  Reward tampering problems and solutions in reinforcement learning: a causal influence diagram perspective , 2019, Synthese.

[9]  Kevin Leyton-Brown,et al.  Temporal Action-Graph Games: A New Representation for Dynamic Games , 2009, UAI.

[10]  Tom Everitt,et al.  How RL Agents Behave When Their Actions Are Modified , 2021, AAAI.

[11]  Ya'akov Gal,et al.  Networks of Influence Diagrams: A Formalism for Representing Agents' Beliefs and Decision-Making Processes , 2008, J. Artif. Intell. Res..

[12]  Shane Legg,et al.  The Incentives that Shape Behaviour , 2020, ArXiv.

[13]  Abinash Panda,et al.  pgmpy: Probabilistic Graphical Models using Python , 2015, SciPy.

[14]  Koen Holtman,et al.  Towards AGI Agent Safety by Iteratively Improving the Utility Function , 2020, AGI.

[15]  A. Rubinstein,et al.  The Absent-Minded Driver's Paradox: Synthesis and Responses , 1997 .

[16]  Daphne Koller,et al.  Multi-Agent Influence Diagrams for Representing and Solving Games , 2001, IJCAI.

[17]  Illtyd Trethowan.  Causality , 1938 .

[18]  Shane Legg,et al.  Agent Incentives: A Causal Perspective , 2021, AAAI.

[19]  Marek Mikolaj Kaminski,et al.  Generalized Backward Induction: Justification for a Folk Algorithm , 2019, Games.

[20]  Andrew McLennan,et al.  Gambit: Software Tools for Game Theory , 2006 .

[21]  Ya'akov Gal,et al.  On the Reasoning Patterns of Agents in Games , 2007, AAAI.

[22]  J. Nash.  Equilibrium Points in N-Person Games. , 1950, Proceedings of the National Academy of Sciences of the United States of America.

[23]  Reinhard Selten.  Spieltheoretische Behandlung eines Oligopolmodells mit Nachfrageträgheit , 2016 .