Reciprocal and Extortive Strategies: Infinitely Iterated Prisoner's Dilemma

Abstract

The Prisoner's Dilemma game has a long history stretching across the social, biological, and physical sciences. In 2012, Press and Dyson developed a method for analyzing the mapping of the 8-dimensional strategy profile onto the 2-dimensional payoff space in an infinitely iterated Prisoner's Dilemma game, based on Markov chain analysis and memory-one strategies. We generalize this approach and introduce the concept of strategy parameter to show that linear relations among player payoffs are a ubiquitous feature of the infinitely iterated Prisoner's Dilemma game. Our extended analysis is applied to various strategy profiles including tit-for-tat, win-stay-lose-shift, and other randomized strategy sets. Strategy profiles are identified that map onto the vertices, edges, and interior of the Prisoner's Dilemma quadrilateral in the 2-dimensional payoff (score) space. A DaMD strategy is defined based solely on "Defection after Mutual Defection" and leads to linear relations between player scores using strategy parameter analysis. The DaMD strategy is shown to result in an equal (reciprocal) or larger (extortive) score for its user compare to the other player, independent of the strategy of the other player. The extortive scores occur when the probabilities for the DaMD player to cooperate after conflicting plays (cooperate-defect or defect-cooperate) sum to less than 1. The equal reciprocal scores occur when the probabilities for the DaMD player to cooperate after conflicting plays (cooperate-defect or defect-cooperate) sum to 1. When one player selects the extortive DaMD, the opposing player can force the equal punishment payoffs for both players in the infinitely iterated Prisoner's dilemma by also choosing the DaMD strategy. Possible pathways to mutual cooperation based on DaMD are discussed.