Co-evolutionary Learning in the N-player Iterated Prisoner’s Dilemma with a Structured Environment

Chiong, Raymond; Kirley, Michael

doi:10.1007/978-3-642-10427-5_4

Cited by 9 publications

(7 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A simple extension to the IPD, which we refer to as the N-IPD game (see [4,7,8,9,11,43]), is to modify the game so that multiple players play a version of the game at the same time. In the N-IPD, N players repeatedly interact with one another (where N > 2), making decisions independently based on two actions -cooperate or defect -without knowing the choices of other players.…”

Section: Iterated N-player Gamesmentioning

confidence: 99%

Iterated n-player games on small-world networks

Chiong

Kirley

2011

Proceedings of the 13th Annual Conference on Genetic and Evolutionary Computation

Self Cite

View full text Add to dashboard Cite

The evolution of strategies in iterated multi-player social dilemma games is studied on small-world networks. Two different games with varying reward values -the N-player Iterated Prisoner's Dilemma (N-IPD) and the N-player Iterated Snowdrift game (N-ISD) -form the basis of this study. Here, the agents playing the game are mapped to the nodes of different network architectures, ranging from regular lattices to small-world networks and random graphs. In a given game instance, the focal agent participates in an iterative game with N − 1 other agents drawn from its local neighbourhood. We use a genetic algorithm with synchronous updating to evolve agent strategies. Extensive Monte Carlo simulation experiments show that for smaller cost-to-benefit ratios, the extent of cooperation in both games decreases as the probability of re-wiring increases. For higher cost-tobenefit ratios, when the re-wiring probability is small we observe an increase in the level of cooperation in the N-IPD population, but not the N-ISD population. This suggests that the small-world network structure with small re-wiring probabilities can both promote and maintain higher levels of cooperation when the game becomes more challenging.

show abstract

Section: Iterated N-player Gamesmentioning

confidence: 99%

Iterated n-player games on small-world networks

Chiong

Kirley

2011

Proceedings of the 13th Annual Conference on Genetic and Evolutionary Computation

Self Cite

View full text Add to dashboard Cite

show abstract

“…Numerous studies in the EGT literature have demonstrated that by restricting the interactions of players to local neighbourhoods/groups (Chiong, Dhakal, & Jankovic, 2007;Chiong & Kirley, 2009, 2011, 2012aKillingback & Doebeli, 1996;Nowak & May, 1992, 1993 or subdividing the population into groups (Killingback, Bieri, & Flatt,, 2006;Nunney, 1985;Traulsen & Nowak, 2006;Wilson 1990), cooperative behaviour can be promoted. Motivated by this, we hope to apply principles and findings from EGT to address issues in online study groups.…”

Section: Evolutionary Game Theorymentioning

confidence: 99%

Collaborative Learning in Online Study Groups: An Evolutionary Game Theory Perspective

Chiong¹,

Jovanović

2012

JITE:Research

Self Cite

View full text Add to dashboard Cite

Executive SummaryEducational benefits of online collaborative group work have been confirmed in numerous research studies. Most frequently cited advantages include the development of skills of critical thinking and problem solving as well as skills of self-reflection and co-construction of knowledge and meaning. However, the establishment and maintenance of active collaboration in online study groups is a challenging task, primarily due to students' inability (e.g., owing to time constraints or lack of collaboration skills) or reluctance (e.g., due to the lack of or low participation of other group members) to participate actively in the group work. Aiming to better understand and contribute to the resolution of the problems of effective online group work, we followed a novel approach based on Evolutionary Game Theory (EGT). While EGT has been used extensively as a framework for studying the emergence and maintenance of cooperation in many disciplines, to the best of our knowledge, it has not yet been applied to understanding and facilitating group collaboration in online learning settings. In this paper, we present a study we have conducted in order to investigate whether, and to what extent, EGT can be applied to explain students' participation in collaborative study groups.

show abstract

“…Here, the heterogeneous graphs enable cooperators to form clusters in some instances, thereby reducing exploitation. Besides this work, a number of authors have also examined the effects of community structure [34], [35] and neighbourhood structure [22], [36] in the context of N-player social dilemmas to promote cooperative behaviour.…”

Section: Spatial Gamesmentioning

confidence: 99%

“…In the case of N = 4, we use a unique triangular neighbourhood structure (see [22]). As for N = 5 and 9, we use the standard von Neumann and Moore neighbourhoods.…”

Section: A Experimental Settings and Parametersmentioning

confidence: 99%

See 1 more Smart Citation

Imitation vs evolution: Analysing the effects of strategy update mechanisms in N-player social dilemmas

Chiong

Kirley

2010

IEEE Congress on Evolutionary Computation

Self Cite

View full text Add to dashboard Cite

The problem of evolving and maintaining cooperation in both ecological and artificial multi-agent systems has intrigued scientists for decades. In this paper, we present an evolutionary game model that combines direct and spatial reciprocity to investigate the effectiveness of two different learning mechanisms used to promote cooperative behaviour in a social dilemma game -the N-player Iterated Prisoner's Dilemma (NIPD). Unlike the two-player game, in the NIPD the action of a player typically results in a non Pareto-optimal outcome for all other players within a social group given the relative costs and benefits associated with particular actions. Consequently, promoting system-wide cooperation is extremely difficult. We use comprehensive Monte Carlo simulation experiments to show that evolutionary-based strategy adaptation and update leads to significantly higher levels of cooperation in the NIPD when compared to social learning via cultural imitation. This finding suggests that when designing decentralised multi-agent systems, evolutionary adaptation mechanisms should be incorporated into the model where efficient collective actions are required.

show abstract

Co-evolutionary Learning in the N-player Iterated Prisoner’s Dilemma with a Structured Environment

Cited by 9 publications

References 11 publications

Iterated n-player games on small-world networks

Iterated n-player games on small-world networks

Collaborative Learning in Online Study Groups: An Evolutionary Game Theory Perspective

Imitation vs evolution: Analysing the effects of strategy update mechanisms in N-player social dilemmas

Contact Info

Product

Resources

About