As a transformative general-purpose technology, AI has empowered various industries and will continue to shape our lives through ubiquitous applications. Despite the enormous benefits from wide-spread AI deployment, it is crucial to address associated downside risks and therefore ensure AI advances are safe, fair, responsible, and aligned with human values. To do so, we need to establish effective AI governance. In this work, we show that the strategic interaction between the regulatory agencies and AI firms has an intrinsic structure reminiscent of a Stackelberg game, which motivates us to propose a game-theoretic modeling framework for AI governance. In particular, we formulate such interaction as a Stackelberg game composed of a leader and a follower, which captures the underlying game structure compared to its simultaneous play counterparts. Furthermore, the choice of the leader naturally gives rise to two settings. And we demonstrate that our proposed model can serves as a unified AI governance framework from two aspects: firstly we can map one setting to the AI governance of civil domains and the other to the safety-critical and military domains, secondly, the two settings of governance could be chosen contingent on the capability of the intelligent systems. To the best of our knowledge, this work is the first to use game theory for analyzing and structuring AI governance. We also discuss promising directions and hope this can help stimulate research interest in this interdisciplinary area. On a high, we hope this work would contribute to develop a new paradigm for technology policy: the quantitative and AI-driven methods for the technology policy field, which holds significant promise for overcoming many shortcomings of existing qualitative approaches.
IT governance, like global governance of projects, requires cooperation between several actors. In general, such cooperation builds a collaboration network between entities. Many works in the literature interested in collaboration network, but no one of them were focused directly on how to build a network in an IT governance perspective. In this paper, we investigate how game theory can be exploited to provide a formal implementation of Cost Management Process, while highlighting Actor-Network as a framework of collaboration and its incentive stage as a key step for network construction. Our o…
This paper deals with the design of the secure blockchain network framework to prevent damages from an attacker. The decentralized network design called the Blockchain Governance Game is a new hybrid theoretical model and it provides the stochastic game framework to find best strategies towards preparation for preventing a network malfunction by an attacker. Analytically tractable results are obtained by using the fluctuation theory and the mixed strategy game theory. These results enable to predict the moment for operations and deliver the optimal portion of backup nodes to protect the blockc…
This paper deals with the design of the secure network in an Enhanced Internet of Vehicles by using the Blockchain Governance Game (BGG). The BGG is a system model of a stochastic game to find best strategies towards preparation of preventing a network malfunction by an attacker and the paper applies this game model into the connected vehicle security. Analytically tractable results for decision-making parameters enable to predict the moment for safety operations and to deliver the optimal combination of the number of reserved nodes with the acceptance probability of backup nodes to protect a …
This research contributes to the security design of an advanced smart drone swarm network based on a variant of the Blockchain Governance Game (BGG), which is the theoretical game model to predict the moments of security actions before attacks, and the Strategic Alliance for Blockchain Governance Game (SABGG), which is one of the BGG variants which has been adapted to construct the best strategies to take preliminary actions based on strategic alliance for protecting smart drones in a blockchain-based swarm network. Smart drones are artificial intelligence (AI)-enabled drones which are capable…
This paper deals with design of the alternative secure Blockchain network framework to prevent damages from an attacker. The concept of the strategic alliance of the management is applied on the top of the recent developed stochastic game framework. This new enhanced hybrid theoretical model has been developed based on the combination of the conventional game theory, the fluctuation theory and the Blockchain Governance Game to find best strategies towards preparation for preventing a network malfunction from an attacker by making the strategic alliance with other genuine miners. Analytically t…
Media and responsible AI governance: a game-theoretic and LLM analysis
University of Birmingham（伯明翰大学）；Teesside University（蒂斯河谷大学）；Luxembourg Institute of Science and Technology（卢森堡科学技术研究院）；University of St Andrews（圣安德鲁斯大学）；INESC-ID；Universidade de Lisboa（里斯本大学）；Vrije Universiteit Brussel（布鲁塞尔自由大学）；University of Stirling（斯特林大学）；University of Trento（特伦托大学）；University of Amsterdam（阿姆斯特丹大学）
Since the recent introduction of several viable vaccines for SARS-CoV-2, vaccination uptake has become the key factor that will determine our success in containing the COVID-19 pandemic. We argue that game theory and social network models should be used to guide decisions pertaining to vaccination programmes for the best possible results. In the months following the introduction of vaccines, their availability and the human resources needed to run the vaccination programmes have been scarce in many countries. Vaccine hesitancy is also being encountered from some sections of the general public.…
An algorithm is proposed to verify whether a finite game is a weighted potential game (WPG) without pre-knowledge on its weights. Then the algorithm is also applied to find the closest WPG for a given finite game. The concept and criterion of near weighted potential games (NWPGs) are given, indicating the evolutionary equivalence between a finite game and its closest WPG. Based on this, a method is proposed for replacing PGs by NWPGs in game theoretic control, which improved the applicability of PG-based optimization.
The off-switch game is a game theoretic model of a highly intelligent robot interacting with a human. In the original paper by Hadfield-Menell et al. (2016), the analysis is not fully game-theoretic as the human is modelled as an irrational player, and the robot's best action is only calculated under unrealistic normality and soft-max assumptions. In this paper, we make the analysis fully game theoretic, by modelling the human as a rational player with a random utility function. As a consequence, we are able to easily calculate the robot's best action for arbitrary belief and irrationality ass…
Peer production, such as the collaborative authoring of Wikipedia articles, involves both cooperation and competition between contributors, and we focus on the latter. As individuals, contributors compete to align Wikipedia articles with their personal perspectives. As a community, they work collectively to ensure a neutral point of view (NPOV). We study the interplay between individuals' competition and the community's endeavor to ensure neutrality. We develop a two-level game-theoretic model, modeling the interactions of ownership-motivated individuals and neutrality-seeking communal mechani…
Many packing, scheduling and covering problems that were previously considered by computer science literature in the context of various transportation and production problems, appear also suitable for describing and modeling various fundamental aspects in networks optimization such as routing, resource allocation, congestion control, etc. Various combinatorial problems were already studied from the game theoretic standpoint, and we attempt to complement to this body of research. Specifically, we consider the bin packing problem both in the classic and parametric versions, the job scheduling pr…
In this paper we study the two-player generalized Cops and Robber (GCR) games introduced by Bonato and MacGillivray. Our main goal is to present a full, self-contained game theoretic analysis of such games.
In this invited contribution, we propose a comprehensive introduction to game theory applied in computer aided synthesis. In this context, we give some classical results on two-player zero-sum games and then on multi-player non zero-sum games. The simple case of one-player games is strongly related to automata theory on infinite words. All along the article, we focus on general approaches to solve the studied problems, and we provide several illustrative examples as well as intuitions on the proofs.
In this article, we introduce a game-theoretic learning framework for the multi-agent wireless network. By combining learning in artificial intelligence (AI) with game theory, several promising properties emerge such as obtaining high payoff in the unknown and dynamic environment, coordinating the actions of agents and making the adversarial decisions with the existence of malicious users. Unfortunately, there is no free lunch. To begin with, we discuss the connections between learning in AI and game theory mainly in three levels, i.e., pattern recognition, prediction and decision making. Then…
The game-theoretic version of Kolmogorov's strong law of large numbers says that Skeptic has a strategy forcing the statement of the law in a game of prediction involving Reality, Forecaster, and Skeptic. This note describes a simple matching strategy for Reality.
In this work, we study the social learning problem, in which agents of a networked system collaborate to detect the state of the nature based on their private signals. A novel distributed graphical evolutionary game theoretic learning method is proposed. In the proposed game-theoretic method, agents only need to communicate their binary decisions rather than the real-valued beliefs with their neighbors, which endows the method with low communication complexity. Under mean field approximations, we theoretically analyze the steady state equilibria of the game and show that the evolutionarily sta…
In this article, the anti-jamming communication problem is investigated from a game-theoretic learning perspective. By exploring and analyzing intelligent anti-jamming communication, we present the characteristics of jammers and the requirements of an intelligent anti-jamming approach. Such approach is required of self-sensing, self-decision making, self-coordination, self-evaluation, and learning ability. Then, a game-theoretic learning anti-jamming (GTLAJ) paradigm is proposed, and its framework and challenges of GTLAJ are introduced. Moreover, through three cases, i.e., Stackelberg anti-jam…
In this paper, we view the Internet under a game-theoretic lens in an effort to explain and overcome the Internet's innovation slump. Game Theory is used to model Internet environments as problems of technological competition toward the end of understanding their emergent phenomena and the evolutionary forces that shape them. However, our results extend beyond understanding the Internet architecture toward helping the Internet population achieve socially desirable outcomes.
Game-theoretic centrality is a flexible and sophisticated approach to identify the most important nodes in a network. It builds upon the methods from cooperative game theory and network theory. The key idea is to treat nodes as players in a cooperative game, where the value of each coalition is determined by certain graph-theoretic properties. Using solution concepts from cooperative game theory, it is then possible to measure how responsible each node is for the worth of the network. The literature on the topic is already quite large, and is scattered among game-theoretic and computer science…
This paper provides theoretical bounds for empirical game theoretical analysis of complex multi-agent interactions. We provide insights in the empirical meta game showing that a Nash equilibrium of the meta-game is an approximate Nash equilibrium of the true underlying game. We investigate and show how many data samples are required to obtain a close enough approximation of the underlying game. Additionally, we extend the meta-game analysis methodology to asymmetric games. The state-of-the-art has only considered empirical games in which agents have access to the same strategy sets and the pay…
We introduce a game-theoretic approach to the study of recommendation systems with strategic content providers. Such systems should be fair and stable. Showing that traditional approaches fail to satisfy these requirements, we propose the Shapley mediator. We show that the Shapley mediator fulfills the fairness and stability requirements, runs in linear time, and is the only economically efficient mechanism satisfying these properties.
In this dissertation, we analyze the computational properties of game-theoretic centrality measures. The key idea behind game-theoretic approach to network analysis is to treat nodes as players in a cooperative game, where the value of each coalition of nodes is determined by certain graph properties. Next, the centrality of any individual node is determined by a chosen game-theoretic solution concept (notably, the Shapley value) in the same way as the payoff of a player in a cooperative game. On one hand, the advantage of game-theoretic centrality measures is that nodes are ranked not only ac…
We introduce versions of game-theoretic semantics (GTS) for Alternating-Time Temporal Logic (ATL). In GTS, truth is defined in terms of existence of a winning strategy in a semantic evaluation game, and thus the game-theoretic perspective appears in the framework of ATL on two semantic levels: on the object level in the standard semantics of the strategic operators, and on the meta-level where game-theoretic logical semantics is applied to ATL. We unify these two perspectives into semantic evaluation games specially designed for ATL. The game-theoretic perspective enables us to identify new va…
In this paper, we propose a game-theoretic solution to the parking problem, by exploiting a strategic-reasoning approach for multi-agent systems. Precisely, cars are modeled by agents interacting among them in a multi-player game setting, whose aim is to get a free slot parking-place satisfying their own constraints. The overall assignment is then given as a Nash equilibrium solution. We come up with an algorithm (and its implementation in a tool) that works in quadratic time. We give evidence of the benefits of our approach by running our tool on a large hospital parking space.
We propose a framework based on Network Formation Game for self-organization in the Internet of Things (IoT), in which heterogeneous and multi-interface nodes are modeled as self-interested agents who individually decide on establishment and severance of links to other agents. Through analysis of the static game, we formally confirm the emergence of realistic topologies from our model, and analytically establish the criteria that lead to stable multi-hop network structures.
A variety of problems in econometrics and machine learning, including instrumental variable regression and Bellman residual minimization, can be formulated as satisfying a set of conditional moment restrictions (CMR). We derive a general, game-theoretic strategy for satisfying CMR that scales to nonlinear problems, is amenable to gradient-based optimization, and is able to account for finite sample uncertainty. We recover the approaches of Dikkala et al. and Dai et al. as special cases of our general framework before detailing various extensions and how to efficiently solve the game defined by…
DeepMind（深度思维）；University College London（伦敦大学学院）；Google（谷歌）；Carnegie Mellon University（卡内基梅隆大学）
Rating strategies in a game is an important area of research in game theory and artificial intelligence, and can be applied to any real-world competitive or cooperative setting. Traditionally, only transitive dependencies between strategies have been used to rate strategies (e.g. Elo), however recent work has expanded ratings to utilize game theoretic solutions to better rate strategies in non-transitive games. This work generalizes these ideas and proposes novel algorithms suitable for N-player, general-sum rating of strategies in normal-form games according to the payoff rating system. This …
It has been shown that a functional interpretation of proofs in mathematical analysis can be given by the product of selection functions, a mode of recursion that has an intuitive reading in terms of the computation of optimal strategies in sequential games. We argue that this result has genuine practical value by interpreting some well-known theorems of mathematics and demonstrating that the product gives these theorems a natural computational interpretation that can be clearly understood in game theoretic terms.
We present a new method for multi-agent planning involving human drivers and autonomous vehicles (AVs) in unsignaled intersections, roundabouts, and during merging. In multi-agent planning, the main challenge is to predict the actions of other agents, especially human drivers, as their intentions are hidden from other agents. Our algorithm uses game theory to develop a new auction, called GamePlan, that directly determines the optimal action for each agent based on their driving style (which is observable via commonly available sensors). GamePlan assigns a higher priority to more aggressive or…
University of Michigan（密歇根大学）；Bilkent University（比尔肯特大学）
In this paper, we propose a decision making algorithm for autonomous vehicle control at a roundabout intersection. The algorithm is based on a game-theoretic model representing the interactions between the ego vehicle and an opponent vehicle, and adapts to an online estimated driver type of the opponent vehicle. Simulation results are reported.
This review presents and reviews various solved and open problems in developing, analyzing, and mitigating epidemic spreading processes under human decision-making. We provide a review of a range of epidemic models and explain the pros and cons of different epidemic models. We exhibit the art of coupling epidemic models and decision models in the existing literature. {More specifically, we provide answers to fundamental questions in human decision-making amid epidemics, including what interventions to take to combat the disease, who are decision-makers, when to take interventions, and how to m…
In (Istrate, Marathe, Ravi SODA 2001) we advocated the investigation of robustness of results in the theory of learning in games under adversarial scheduling models. We provide evidence that such an analysis is feasible and can lead to nontrivial results by investigating, in an adversarial scheduling setting, Peyton Young's model of diffusion of norms. In particular, our main result incorporates into Peyton Young's model.
Ganzfried Research（甘茨弗里德研究公司）；Florida International University（佛罗里达国际大学）
Creating strong agents for games with more than two players is a major open problem in AI. Common approaches are based on approximating game-theoretic solution concepts such as Nash equilibrium, which have strong theoretical guarantees in two-player zero-sum games, but no guarantees in non-zero-sum games or in games with more than two players. We describe an agent that is able to defeat a variety of realistic opponents using an exact Nash equilibrium strategy in a 3-player imperfect-information game. This shows that, despite a lack of theoretical guarantees, agents based on Nash equilibrium st…
The game-theoretic risk management framework put forth in the precursor work "Towards a Theory of Games with Payoffs that are Probability-Distributions" (arXiv:1506.07368 [q-fin.EC]) is herein extended by algorithmic details on how to compute equilibria in games where the payoffs are probability distributions. Our approach is "data driven" in the sense that we assume empirical data (measurements, simulation, etc.) to be available that can be compiled into distribution models, which are suitable for efficient decisions about preferences, and setting up and solving games using these as payoffs. …
