The prisoner's dilemma (PD) is the leading metaphor for the evolution of cooperative behavior in populations of selfish agents. Although cooperation in the iterated prisoner's dilemma (IPD) has been studied for over twenty years, most of this research has been focused on strategies that involve nonlearned behavior. Another approach is to suppose that players' selection of the preferred reply might be enforced in the same way as feeding animals track the best way to feed in changing nonstationary environments. Learning mechanisms such as operant conditioning enable animals to acquire relevant characteristics of their environment in order to get reinforcements and to avoid punishments. In this study, the role of operant conditioning in the learning of cooperation was evaluated in the PD. We found that operant mechanisms allow the learning of IPD play against other strategies. When random moves are allowed in the game, the operant learning model showed low sensitivity. On the basis of this evidence, it is suggested that operant learning might be involved in reciprocal altruism.

Artificial intelligence researchers have been attracted by the idea of having robots learn how to accomplish a task, rather than being told explicitly. Reinforcement learning has been proposed as an appealing framework to be used in controlling mobile agents. Robot learning research, as well as research in biological systems, face many similar problems in order to display high flexibility in performing a variety of tasks. In this work, the controlling of a vehicle in an avoidance task by a previously developed operant learning model (a form of animal learning) is studied. An environment in which a mobile robot with proximity sensors has to minimize the punishment for colliding against obstacles is simulated. The results were compared with the Q-Learning algorithm, and the proposed model had better performance. In this way a new artificial intelligence agent inspired by neurobiology, psychology, and ethology research is proposed.