R. Axelrod. The evolution of strategies in the iterated prisoner's dilemma. In L. Davis, editor, Genetic Algorithms and Simulated Annealing, Research Notes in Artificial Intelligence, pages 32--41, London, 1987. Pitman Publishing.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....This cooperation occurs despite a bloodthirsty option offering more payoff to those might exploit their more cooperative peers. Some situations offer only two choices, either full conflict or full cooperation, with nothing in between. This simple two choice case is the most studied [1] [2] [8] 18] The real world is often more complicated, with intermediate degrees of cooperation, rather than all or nothing [11] 22, page 175] This complicates the emergence of cooperation. Why this is so, is the topic of this paper. 1.1 Iterated Prisoner s Dilemma To better understand how ....

....# # ## # ## (3) 1. 3 Co Evolutionary Learning To gain insight into why mutual cooperation does or does not emerge in IPD, current research follows political scientist Robert Axelrod, who imposed a co evolutionary dynamic on a population of trial strategies playing against each other [2]. In this approach, a computer maintains a population of trial strategies. An evaluation function judges the quality of each trial strategy in the population. Instead of a human programmer writing that evaluation function, in co evolution a strategy s fitness is evaluated by its peers in the same ....

[Article contains additional citation context not shown here]

Robert M. Axelrod. The evolution of strategies in the iterated prisoner's dilemma. In Genetic Algorithms and Simulated Annealing, chapter 3, pages 32--41. Morgan Kaufmann, 1987.

....for the 2 player game under various conditions [1] The focus of this paper will be on co evolutionary learning and the generalization ability of learned strategies. 2. 2 Representation of Strategies The evolutionary approach to strategy learning for the 2IPD game was popularized by Axelrod [2]. One of the most important issues in evolving game playing strategies is their representation. There are two different possible representations for N player IPD games (N 2) 3, 4] One is based on a generalization of Axelrod s representation scheme for the 2 player game. For the N player game, ....

R. Axelrod, "The evolution of strategies in the iterated prisoner's dilemma," in Genetic Algorithms and Simulated Annealing (L. Davis, ed.), ch. 3, pp. 32--41, San Mateo, CA: Morgan Kaufmann, 1987.

....Jong[15] describe an architecture for cooperative coevolution, in which individuals in one species are evaluated by using collaborators from each of the other coevolving species. There exist a number of logical possibilities for choosing collaborators: All invididuals of each of the other species[16], but this is time consuming and can lead to a combinatorial explosion if there are many species. The best individuals of each of the other species in the last generation[17] Randomly drawn individual(s) of each of the other species in the same generation[18] 19] With a fixed parmer (or ....

Axelrod, R. 1987. The evolution of strategies in the iterated prisoner's dilemma. In L.D. Davis, (Ed.), Genetic Algorithms and Simulated Annealing, 32-41. New York, Morgan Kaufmann.

....Angeline and Pollack [1] enumerate potential advantages of competitive fitness functions and argue that they are a powerful unexplored resource in genetic algorithms. They describe three types of competitive fitness functions as examples. The first is a full competition model used by Axelrod [2] to evolve strategies for the Iterated Prisoner s Dilemma. The second is a bipartite competition that Hillis [11] used to evolve sorting networks. The third type, which they present themselves, is tournament fitness, which they use to evolve modular programs to play Tic Tac Toe. In the full ....

....Iterated Prisoner s Dilemma. The second is a bipartite competition that Hillis [11] used to evolve sorting networks. The third type, which they present themselves, is tournament fitness, which they use to evolve modular programs to play Tic Tac Toe. In the full competition model used by Axelrod [2], every population member is tested against every other population member. Assuming the size of the population is n, the number of competitions executed in a generation is n . According to Angeline and Pollack, this number of competitions may be prohibitive when the task to be solved is complex ....

Robert Axelrod. The evolution of strategies in the iterated prisoner's dilemma. In L. Davis, editor, Genetic Algorithms and Simulated Annealing. Morgan Kaufman, 1989.

....and the iterated prisoner s dilemma respectively. Binmore [7] provides a critical review on the problem of simulating evolution and cooperation based on the studies performed by Axelrod. Simulations of co evolving populations in competitive environments have been implemented [8] [9]. For example Sims [10] reported a genetic algorithm approach to evolving 3D morphology and behaviour. The morphology of artificial creatures and their neural systems for controlling their movements are both genetically constructed. They define a genetic model that applies directed graphs to ....

R. Axelrod, "Evolution of strategies in the iterated prisoner's dilemma", in Genetic Algorithms and Simulated Annealing, ed. by L. Davis, Morgan Kaufmann: London, 1987, pp. 32-41.

....known result is that, when a succession of cooperation opportunities involves a small number of cooperators, cooperation naturally emerges as a consequence of reciprocity. A both theoretically and experimentally well studied model of this mechanism is the two player Iterated Prisoners Dilemma [1, 3, 5, 10, 7]. Unfortunately, as envisaged by Hardin [9] when the opportunity requires more than a handful of cooperating participants, the reciprocity mechanism that is responsible for the stability of the cooperative behavior is weakened, and cooperators are open to exploita tion [8, 4] Experimental ....

Robert M. Axelrod. The evolution of strategies in the iterated prisoner's dilemma. In Lawrence Davis, editor, Genetic Algorithms and Simulated Annealing, chapter 3, pages 32 41. Morgan Kaufmann, Los Altos, Calif., 1987.

....known result is that, when a succession of cooperation opportunities involves a small number of cooperators, cooperation naturally emerges as a consequence of reciprocity. A both theoretically and experimentally well studied model of this mechanism is the two player Iterated Prisoners Dilemma [1, 3, 7, 5, 6, 18, 10]. Unfortunately, as envisaged by Hardin [14] when the opportunity requires more than a handful of cooperating participants, the reciprocity mechanism that is responsible for the stability of the cooperative behavior is weakened, and cooperators are open to exploitation [13, 4] Experimental ....

R. M. Axelrod. The evolution of strategies in the iterated prisoner's dilemma. In L. Davis, editor, Genetic Algorithms and Simulated Annealing, chapter 3, pages 32-41. Morgan Kaufmann, Los Altos, Calif., 1987.

....know when the game is supposed to end. One of the most important issues in evolving game playing strategies is their representation. There are two di erent possible representations [2, 5] both of which are lookup tables that give an action for every possible contingency. In this paper, Axelrod [1] for the 2IPD game is used. In this scheme, each genotype is a lookup table that covers every possible history of the last few steps. History in such a game is represented as a binary string of 2l bits, where the rst l bits represent the player s own previous l actions (most recent to the left, ....

R. Axelrod, \The evolution of strategies in the iterated prisoner's dilemma," in Genetic Algorithms and Simulated Annealing (L. Davis, ed.), ch. 3, pp. 32-41, San Mateo, CA: Morgan Kaufmann, 1987.

....known result is that, when a succession of cooperation opportunities involves a small number of cooperators, cooperation naturally emerges as a consequence of reciprocity. A both theoretically and experimentally well studied model of this mechanism is the two player Iterated Prisoners Dilemma [1, 3, 5, 10, 7]. Unfortunately, as envisaged by Hardin [9] when the opportunity requires more than a handful of cooperating participants, the reciprocity mechanism that is responsible for the stability of the cooperative behavior is weakened, and cooperators are open to exploitation [8, 4] Experimental ....

Robert M. Axelrod. The evolution of strategies in the iterated prisoner's dilemma. In Lawrence Davis, editor, Genetic Algorithms and Simulated Annealing, chapter 3, pages 32-41. Morgan Kaufmann, Los Altos, Calif., 1987.

....important to realworld applications, than are deterministic toy problems. Co evolutionary learning can discover solutions to problems, without prior knowledge from human experts. The method has achieved impressive results, both on games such as Checkers [3] and the iterated Prisoner s Dilemma [1] [6] 7] as well as in other tasks [12] 17] such as creating a sorting algorithm [10] and schedule optimization [11] The question facing this paper is, for a given solution representation, how can co evolutionary learning obtain the highest skill from the least CPU time on a noisy task with ....

Robert M. Axelrod. The evolution of strategies in the iterated prisoner's dilemma. In Genetic Algorithms and Simulated Annealing, chapter 3, pages 32--41. Morgan Kaufmann, 1987.

No context found.

R. Axelrod. The evolution of strategies in the iterated prisoner's dilemma. In L. Davis, editor, Genetic Algorithms and Simulated Annealing, Research Notes in Artificial Intelligence, pages 32--41, London, 1987. Pitman Publishing.

No context found.

Axelrod, R. "The evolution of strategies in the iterated prisoner's dilemma", in Genetic Algorithms and Simulated Annealing (L. Davis, Ed.), Pitman, 1987.

No context found.

Axelrod, R., The evolution of strategies in the iterated prisoner's dilemma, in Davis, L. (ed.), Genetic algorithms and simulated annealing, Research notes in AI, Pitman/Morgan Kaufmann, 1987, 32-41

No context found.

Robert Axelrod, The Evolution of Strategies in the Iterated Prisoner's Dilemma, in Davis, L. (ed.), Genetic algorithms and simulated annealing, Research notes in AI, Pitman/Morgan Kaufmann, 1987, 32-41

No context found.

R. Axelrod. The evolution of strategies in the iterated prisoner's dilemma. In Lawrence Davis, editor, Genetic algorithms and simulated annealing, pages 32--41. Morgan Kaufman, 1987.

No context found.

Robert Axelrod. The evolution of strategies in the iterated prisoner's dilemma. In Lawrence Davis, editor, Genetic Algorithms and Simulated Annealing, Research Notes in Artificial Intelligence, pages 32--41, London, 1987. Pitman Publishing.

No context found.

Axelrod, R.: The evolution of strategies in the iterated prisoner's dilemma. In Davis, L., ed.: Genetic Algorithms and Simulated Annealing. Research Notes in Artificial Intelligence, London, Pitman Publishing (1987) 32--41

No context found.

Robert Axelrod. The evolution of strategies in the iterated prisoner's dilemma. In Lawrence Davis, editor, Genetic Algorithms and Simulated Annealing, Research Notes in Artificial Intelligence, pages 32--41, London, 1987. Pitman Publishing.

No context found.

Axelrod, R., The evolution of strategies in the iterated prisoner's dilemma, in Davis, L. (ed.), Genetic algorithms and simulated annealing, Research notes in AI , Pitman/Morgan Kaufmann, 1987, 32-41

No context found.

Robert M. Axelrod. The evolution of strategies in the iterated prisoner's dilemma. In Lawrence Davis, editor, Genetic Algorithms and Simulated Annealing, chapter 3, pages 32-41. Morgan Kaufmann, Los Altos, California, 1987.

No context found.

Axelrod, R. "The evolution of strategies in the iterated prisoner's dilemma", in Genetic Algorithms and Simulated Annealing (L. Davis, Ed.), Pitman, 1987.

No context found.

R. Axelrod. The evolution of strategies in the iterated prisoner's dilemma. In L. D. Davis, editor, Genetic Algorithms and Simulated Annealing, chapter 3, pages 32-41. Morgan Kaufman, 1987.

No context found.

R. Axelrod, "The evolution of strategies in the Iterated Prisoner's Dilemma," in L. Davis (ed.), Genetic Algorithms and Simulated Annealing, Morgan Kaufmann, Los Altos, pp. 32-41, 1987. -23-

No context found.

R. Axelrod, The evolution of strategies in the Iterated Prisoner's Dilemma, in: L. Davis (ed.), Genetic Algorithms and Simulated Annealing, Morgan Kaufmann, Los Altos, 1987, pp. 32-41.

No context found.

Robert Axelrod. The evolution of strategies in the iterated prisoner's dilemma. Cambridge University Press, 1996. forthcoming.

First 50 documents  Next 50

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC