Disarmament Games

Authors: Yuan Deng, Vincent Conitzer

AAAI 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical In this paper, we first formalize the idea of a disarmament game, as played on top of a game represented in normal form (as illustrated in Example 1). We introduce the computational problem DISARM, which asks whether there is an equilibrium of the disarmament game leading to some desired specified outcome, and a variant K-DISARM in which there are only K rounds of disarmament. We show both problems to be NP-complete. We then introduce a mixed disarmament variant that allows the removal of mixed strategies, by upper-bounding the probabilities on individual pure strategies. Here our results are positive: we show a type of folk theorem holds (without repetition of the game!), namely that for any feasible utilities that exceed players security levels, there is an equilibrium achieving at least those utilities. Our proof is constructive, and in fact shows that we can approximately obtain the desired result in approximate equilibrium using only few rounds of disarmament.
Researcher Affiliation Academia Yuan Deng, Vincent Conitzer Department of Computer Science Duke University Durham, NC 27708, USA {ericdy,conitzer}@cs.duke.edu
Pseudocode Yes Algorithm 1: Generate on-path strategy for feasible utilities that exceed security levels
Open Source Code No The paper does not provide any statement or link indicating the availability of open-source code for the methodology described.
Open Datasets No The paper is theoretical and does not involve training models on datasets. Therefore, no information about publicly available training datasets is provided.
Dataset Splits No The paper is theoretical and does not involve empirical experiments with dataset splits. Therefore, no information about validation splits is provided.
Hardware Specification No The paper does not specify any hardware used for experiments, as it focuses on theoretical analysis and algorithm design.
Software Dependencies No The paper does not provide specific software dependencies with version numbers. It mentions linear programming but not a particular solver or its version.
Experiment Setup No The paper does not describe an experimental setup with hyperparameters or system-level training settings, as it presents theoretical work and algorithms rather than empirical experiments.