Cooperative games are those in which both agents share the same payoff structure. Valuebased reinforcement-learning algorithms, such as variants of Q-learning, have been applied to learning cooperative games, but they only apply when the game state is completely observable to both agents. Policy search methods are a reasonable alternative to value-based methods for partially observable environm...

This study investigated the effects of gameplaying on fifth-graders’ maths performance and attitudes. One hundred twenty five fifth graders were recruited and assigned to a cooperative Teams-Games-Tournament (TGT), interpersonal competitive or no gameplaying condition. A state standardsbased maths exam and an inventory on attitudes towards maths were used for the pretest and posttest. The stude...

My primary research interest is social behavior of software agents acting in general-sum normal form games. In an environment with another agent, an agent needs to be able to identify if the opponent is hostile or cooperative by looking at the opponent’s actions, and respond appropriately. If the opponent is hostile, the agent should guard against it. Even for a self-interested agent, cooperati...

A ‘power index’ is a concept in cooperative game theory. Power indices are used as a measure for the influence that a player has in a certain class of cooperative games called simple games. As the title says, this is a survey on how to compute these power indices. Generally speaking, computing these indices is a tedious task, even for relatively small cooperative games. It is certainly intracta...

This paper presents a new cooperative equilibrium for strategic form games, denoted Conjectural Cooperative Equilibrium (CCE). This concept is based on the expectation that joint deviations from any strategy profile are followed by an optimal and noncooperative reaction of non deviators. We show that CCE exist for all symmetric supermodular games. Furthermore, we discuss the existence of a CCE ...

Building on the work of Nash, Harsanyi, and Shapley, we define a cooperative solution for strategic games that takes account of both the competitive and the cooperative aspects of such games. We prove existence in the general (NTU) case and uniqueness in the TU case. Our main result is an extension of the definition and the existence and uniqueness theorems to stochastic games discounted or und...

In this paper, a generalized form of the Banzhaf-Owen value for cooperative fuzzy games with a coalition structure is proposed. Its axiomatic system is given by extending crisp case. In order to better understand the Banzhaf-Owen value for fuzzy games with a coalition structure, we briefly introduce the Banzhaf-Owen values for two special kinds of fuzzy games with a coalition structure, and giv...