We present tournament results and several powerful strategies for the Iterated Prisoner’s Dilemma created using reinforcement learning techniques (evolutionary and particle swarm algorithms). These strategies are trained to perform well against a corpus of over 170 distinct opponents, including many well-known and classic strategies. All the trained strategies win standard tournaments against the total collection of other opponents. The trained strategies and one particular human made designed strategy are the top performers in noisy tournaments also.

This manuscript explores the research topics and collaborative behaviour of authors in the field of the Prisoner’s Dilemma using topic modeling and a graph theoretic analysis of the co-authorship network. The analysis identified five research topics in the Prisoner’s Dilemma which have been relevant over the course of time. These are human subject research, biological studies, strategies, evolutionary dynamics on networks and modeling problems as a Prisoner’s Dilemma game. Moreover, the results demonstrated the Prisoner’s Dilemma is a field of continued interest, and that it is a collaborative field compared to other game theoretic fields. The co-authorship network suggests that authors are focused on their communities and that not many connections across the communities are made. The most central authors of the network are the authors connected to the main cluster. Through examining the networks of topics, it was uncovered that the main cluster is characterised by the collaboration of authors in a single topic. These findings add to the bibliometrics study in another field and present new questions and avenues of research to understand the reasons for the measured behaviours.

Memory-one strategies are a set of Iterated Prisoner’s Dilemma strategies that have been praised for their mathematical tractability and performance against single opponents. This manuscript investigates best response memory-one strategies with a theory of mind for their opponents. The results add to the literature that has shown that extortionate play is not always optimal by showing that optimal play is often not extortionate. They also provide evidence that memory-one strategies suffer from their limited memory in multi agent interactions and can be out performed by optimised strategies with longer memory. We have developed a theory that has allowed to explore the entire space of memory-one strategies. The framework presented is suitable to study memory-one strategies in the Prisoner’s Dilemma, but also in evolutionary processes such as the Moran process. Furthermore, results on the stability of defection in populations of memory-one strategies are also obtained.