Payoff Function Of Player Research Articles

One-armed bandit problem and the mirror descent algorithm

We consider the application of the mirror descent algorithm (MDA) to the one-armed bandit problem in the minimax statement as applied to data processing. This problem is also known as the game with nature, where the player's payoff function is the mathematical expectation of the total income. The player must determine the most effective method of the two available and provide that it is predominantly used. In this case, the a priori efficiency of one of the methods is known. This article proposes a modification of the MDA that allows to improve the efficiency of control through the use of additional a priori information. The proposed strategy retains the characteristic property of strategies for one-armed bandits - if a known action is applied once, it will be applied until the end of the control. Modifications for the algorithm for one-by-one processing and for its batch version are considered. Batch processing is interesting in that the total processing time is determined by the number of batches and not the original amount of data, if it is possible to provide parallel processing of data in batches. For the proposed algorithms, using the Monte-Carlo simulation, the optimal values of the tunable parameters were calculated and the minimax risk estimates were obtained.

Lower bounds for the query complexity of equilibria in Lipschitz games

Nearly a decade ago, Azrieli and Shmaya introduced the class of λ-Lipschitz games in which every player's payoff function is λ-Lipschitz with respect to the actions of the other players. They showed that such games admit ϵ-approximate pure Nash equilibria for certain settings of ϵ and λ. They left open, however, the question of how hard it is to find such an equilibrium. In this work, we develop a query-efficient reduction from more general games to Lipschitz games. We use this reduction to show a query lower bound for any randomized algorithm finding ϵ-approximate pure Nash equilibria of n-player, binary-action, λ-Lipschitz games that is exponential in nλ/ϵ. In addition, we introduce “Multi-Lipschitz games,” a generalization involving player-specific Lipschitz values, and provide a reduction from finding equilibria of these games to finding equilibria of Lipschitz games, showing that the value of interest is the average of the individual Lipschitz parameters. Finally, we provide an exponential lower bound on the deterministic query complexity of finding ϵ-approximate Nash equilibria of n-player, m-action, λ-Lipschitz games for strong values of ϵ, motivating the consideration of explicitly randomized algorithms in the above results.

Nash equilibrium and group strategy consensus of networked evolutionary game with coupled social groups

This paper studies the existence of Nash equilibrium and group strategy consensus problem of networked evolutionary game with coupled social groups, which is formulated as a two-layer networked game. First, by the approach of semi-tensor product, the payoff functions of players are converted into the algebraic forms, and two necessary and sufficient conditions are derived for the existence of pure Nash equilibrium. Second, the strict game algebraic equation by the best response adjustment rule with group intelligence is established, by which the group strategy consensus problem is investigated. At last, an example is worked out to verify our conclusions.

Adversarial Deep Learning Models with Multiple Adversaries

We develop an adversarial learning algorithm for supervised classification in general and Convolutional Neural Networks (CNN) in particular. The algorithm's objective is to produce small changes to the data distribution defined over positive and negative class labels so that the resulting data distribution is misclassified by the CNN. The theoretical goal is to determine a manipulating change on the input data that finds learner decision boundaries where many positive labels become negative labels. Then we propose a CNN which is secure against such unforeseen changes in data. The algorithm generates adversarial manipulations by formulating a multiplayer stochastic game targeting the classification performance of the CNN. The multiplayer stochastic game is expressed in terms of multiple two-player sequential games. Each game consists of interactions between two players—an intelligent adversary and the learner CNN—such that a player's payoff function increases with interactions. Following the convergence of a sequential noncooperative Stackelberg game, each two-player game is solved for the Nash equilibrium. The Nash equilibrium finds a pair of strategies (learner weights and evolutionary operations) from which there is no incentive for either learner or adversary to deviate. We then retrain the learner over all the adversarial manipulations generated by multiple players to propose a secure CNN which is robust to subsequent adversarial data manipulations. The adversarial data and corresponding CNN performance is evaluated on MNIST handwritten digits data. The results suggest that game theory and evolutionary algorithms are very effective in securing deep learning models against performance vulnerabilities simulated as attack scenarios from multiple adversaries.

An optimization model of three-player payoff based on fuzzy game theory in green supply chain

In this paper an optimization fuzzy game model of three-player payoff is developed, that is affected by customer demands in a green supply chain. This model proposes a practical solution to increase the players’ confidence to choose green strategies. At first, the strategies of players: government, manufacturer and customer are formulated by using game theory and then, in order to optimize the player's payoff function in uncertain conditions of customer demand, the model is combined with fuzzy sets theory in related variables and parameters. Finally, a method of problem solving is presented by Nash equilibrium. To speed up calculations and problem solving, a computational fuzzy program is designed with the capability of sensitive analysis by changing the fuzzy variables and parameters. This model is particularly designed for governments and manufacturers to analyze the effect of customer’s decisions on their strategies, related income/cost parameters that results in the optimized strategy selection, and improved payoff. For the evaluation of the model, a numeral analysis is presented to compare the positive effects of this fuzzy game model on players’ payoff function optimization in uncertain conditions against the non-fuzzy game model.

Estimation of games with ordered actions: An application to chain-store entry

We study the estimation of static games where players are allowed to have ordered actions, such as the number of stores to enter into a market. Assuming that payoff functions satisfy general shape restrictions, we show that equilibrium of the game implies a covariance restriction between each player's action and a component of the player's payoff function that we call the strategic index. The strategic index captures the direction of strategic interaction (i.e., patterns of substitutability or complementarity) as well as the relative effects of opponents' decisions on players' payoffs. The covariance restriction we derive is robust to the presence of multiple equilibria, and provides a basis for identification and estimation of the strategic index. We introduce an econometric method for inference in our model that exploits the information in moment inequalities in a computationally simple way. We analyze its properties through Monte Carlo experiments and then apply our approach to study entry behavior by chain stores where there is both an intensive margin of entry (how many stores to open in a market) as well as the usual extensive margin of entry (whether to enter a market or not). Using data from retail pharmacies we find evidence of asymmetries in strategic effects among firms in the industry that has implications for merger policy. We also find that business stealing effects are less pronounced in larger markets, which helps explain the large positive correlation in entry behavior observed in the data. Static games multiple equilibria partial identification conditional moment inequalities entry decisions C01 C14 C57

Estimation of games with ordered actions: An application to chain‐store entry

We study the estimation of static games where players are allowed to have ordered actions, such as the number of stores to enter into a market. Assuming that payoff functions satisfy general shape restrictions, we show that equilibrium of the game implies a covariance restriction between each player's action and a component of the player's payoff function that we call the strategic index. The strategic index captures the direction of strategic interaction (i.e., patterns of substitutability or complementarity) as well as the relative effects of opponents' decisions on players' payoffs. The covariance restriction we derive is robust to the presence of multiple equilibria, and provides a basis for identification and estimation of the strategic index. We introduce an econometric method for inference in our model that exploits the information in moment inequalities in a computationally simple way. We analyze its properties through Monte Carlo experiments and then apply our approach to study entry behavior by chain stores where there is both an intensive margin of entry (how many stores to open in a market) as well as the usual extensive margin of entry (whether to enter a market or not). Using data from retail pharmacies we find evidence of asymmetries in strategic effects among firms in the industry that has implications for merger policy. We also find that business stealing effects are less pronounced in larger markets, which helps explain the large positive correlation in entry behavior observed in the data. Static games multiple equilibria partial identification conditional moment inequalities entry decisions C01 C14 C57

Bayesian Estimation of Entry Games with Multiple Players and Multiple Equilibria

Entry game models are often used to study the nature of firms' profits and the nature of competition among firms in empirical studies. However, when there are multiple players in an oligopoly market, the resulting multiple equilibria have made it difficult in previous studies to estimate the payoff functions of players in complete information, static and discrete games without using unreasonable assumptions. To overcome this difficulty, the present paper proposes a practical estimation method for an entry game with three players using a Bayesian approach. Some mild assumptions are imposed on the payoff function, and the average competitive effect is used to capture the entry effect of the number of firms. Our proposed methodology is applied to Japanese airline data from the year 2000, when there were three major airline companies, ANA, JAL and JAS. The model comparison is conducted to investigate the nature of strategic interaction among these Japanese airline companies.

Bayesian Games with Baire Class 1 Payoff Functions

This paper considers Bayesian games where a player's payoff function is a Baire class 1 function. A Baire class 1 function (Baire (1905) is defined as a pointwise limit of a sequence of continuous functions and include semicontinuous functions, step functions, functions of bounded variations, and monotone functions. Bayesian games with Baire class 1 payoff's generalize the canonical model of Milgrom and Weber (1985) and encompass a large class of auction games and mechanism design problems. A Bayesian game with Baire class 1 payoff's has a Bayesian equilibrium via continuous approximations when the better reply security condition of Reny (1999) is satisfied. This continuous approximation approach can be regarded as a generalization of the path-following method to games with discontinuous payoff's. Using the continuous approximation method, we characterize the optimal auction mechanism with heterogeneous objects and multidimensional types with continuous distributions by unifying Myerson (1981), Mussa and Rosen (1978), and Rochet and Chone (1998). We illustrate the method by solving an example where the buyers private values are uniformly distributed on a square.

Cooperative Mean-Field Type Games

In the standard formulation of a game, a player's payoff function depends on the states and actions of all the players. Yet, real world applications suggest to consider also a functional of the probability measure of states and actions of all the players. In this paper, we consider cooperative mean-field type games in which the state dynamics and the payoffs depend not only on the state and actions but also on their probability measure. We establish stochastic maximum principle and provide a time-dependent payoff allocation procedure for coalitions. The allocated payoff considers not only fairness property but also the cost of making the coalition. Finally, time consistency and subgame perfectness solution concept equations are established.

Existence of a pure strategy equilibrium in finite symmetric games where payoff functions are integrally concave

In this paper we show that a finite symmetric game has a pure strategy equilibrium if the payoff functions of players are integrally concave due to Favati and Tardella (1990). Since the payoff functions of any two-strategy game are integrally concave, this generalizes the result of Cheng et al. (2004). A simple algorithm to find a pure strategy equilibrium is also provided.

On the existence of pure-strategy perfect equilibrium in discontinuous games

We provide sufficient conditions for a (possibly) discontinuous normal-form game to possess a pure-strategy trembling-hand perfect equilibrium. We first show that compactness, continuity, and quasiconcavity of a game are too weak to warrant the existence of a pure-strategy perfect equilibrium. We then identify two classes of games for which the existence of a pure-strategy perfect equilibrium can be established: (1) the class of compact, metric, concave games satisfying upper semicontinuity of the sum of payoffs and a strengthening of payoff security; and (2) the class of compact, metric games satisfying upper semicontinuity of the sum of payoffs, strengthenings of payoff security and quasiconcavity, and a notion of local concavity and boundedness of payoff differences on certain subdomains of a player's payoff function. Various economic games illustrate our results.

Theorem of the Maximin and Applications to Bayesian Zero-Sum Games

Consider a family of zero-sum games indexed by a parameter that determines each player's payoff function and feasible strategies. Our first main result characterizes continuity assumptions on the payoffs and the constraint correspondence such that the equilibrium value and strategies depend continuously and upper hemicontinuously (respectively) on the parameter. This characterization uses two topologies in order to overcome a topological tension that arises when players' strategy sets are infinite-dimensional. Our second main result is an application to Bayesian zero-sum games in which each player's information is viewed as a parameter. We model each player's information as a sub-sigma-field, so that it determines her feasible strategies: those that are measurable with respect to the player's information. We thereby characterize conditions under which the equilibrium value and strategies depend continuously and upper hemicontinuously (respectively) on each player's information. This clarifies and extends related results of Einy et al. (2008).

A general structure theorem for the Nash equilibrium correspondence

I consider n-person normal form games where the strategy set of each player is a non-empty compact convex subset of an Euclidean space, and the payoff function of player i is continuous in joint strategies and continuously differentiable and concave in the player i's strategy. No further restrictions (such as multilinearity of the payoff functions or the requirement that the strategy sets be polyhedral) are imposed. I demonstrate that the graph of the Nash equilibrium correspondence on this domain is homeomorphic to the space of games. This result generalizes a well-known structure theorem in [Kohlberg, E., Mertens, J.-F., 1986. On the strategic stability of equilibria. Econometrica 54, 1003–1037]. It is supplemented by an extension analogous to the unknottedness theorems in [Demichelis S., Germano, F., 2000. Some consequences of the unknottedness of the Walras correspondence. J. Math. Econ. 34, 537–545; Demichelis S., Germano, F., 2002. On (un)knots and dynamics in games. Games Econ. Behav. 41, 46–60]: the graph of the Nash equilibrium correspondence is ambient isotopic to a trivial copy of the space of games.