Learning to cooperate in the Iterated Prisoner’s Dilemma by means of social attachments

Bazzan, Ana L. C.; Peleteiro, Ana; Burguillo, Juan C.

doi:10.1007/s13173-011-0038-2

Cited by 13 publications

(25 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Application of these methods makes the model much more complex. Another solution is proposed by Bazzan et al (2011). Low-level agents are supervised by tutors that observe low-level agents.…”

Section: Related Researchmentioning

confidence: 99%

A strategy learning model for autonomous agents based on classification

Śnieżyński

2015

International Journal of Applied Mathematics and Computer Science

View full text Add to dashboard Cite

In this paper we propose a strategy learning model for autonomous agents based on classification. In the literature, the most commonly used learning method in agent-based systems is reinforcement learning. In our opinion, classification can be considered a good alternative. This type of supervised learning can be used to generate a classifier that allows the agent to choose an appropriate action for execution. Experimental results show that this model can be successfully applied for strategy generation even if rewards are delayed. We compare the efficiency of the proposed model and reinforcement learning using the farmer-pest domain and configurations of various complexity. In complex environments, supervised learning can improve the performance of agents much faster that reinforcement learning. If an appropriate knowledge representation is used, the learned knowledge may be analyzed by humans, which allows tracking the learning process.

show abstract

Section: Related Researchmentioning

confidence: 99%

A strategy learning model for autonomous agents based on classification

Śnieżyński

2015

International Journal of Applied Mathematics and Computer Science

View full text Add to dashboard Cite

show abstract

“…In this experiment, we do not include other learning based approaches for the evolution of cooperation for comparison. This is because, as Bazzan et al [34] have concluded, it is difficult to directly use learning based approaches in the iterated PD game, because learning based approaches will converge to the Nash equilibrium, which means mutual defection. 3 Bazzan et al also proposed a supervised learning approach, which did enhance cooperation.…”

Section: Experiments and Analysismentioning

confidence: 99%

A Self-Adaptive Strategy for Evolution of Cooperation in Distributed Networks

Zhang

2015

IEEE Trans. Comput.

View full text Add to dashboard Cite

This paper studies the phenomenon of the evolution of cooperation in distributed networks by using an iterated game. An iterated game in a distributed network is a multiple round game, where in each round, a player gains a payoff by playing a game with its neighbours and updates its action based on the actions and/or payoffs of its neighbours. The interaction model between players is usually represented as a two-player, two-action (namely cooperation and defection) Prisoner's Dilemma game (which is a prototypical model for interaction between selfish individuals). Many researchers have developed strategies (also called update rules) for the evolution of cooperation in distributed networks in order to enhance cooperation, i.e., to increase the proportion of cooperators. Experimental results reported in the current literature, however, have demonstrated that each of these strategies has both advantages and disadvantages. In this paper, a self-adaptive strategy is proposed for the evolution of cooperation in distributed networks, which can utilise the strengths and avoid the limitations of existing strategies. Moreover, we have a theoretical finding about the final proportion of cooperators, evolved by any pure (or deterministic) strategies, in four types of a game. This finding is independent of the initial proportion of cooperators, the topology of the network (e.g., a small-world network or a scale-free network), and the specific game (e.g., the Prisoner's Dilemma game or the Snow Drift game).

show abstract

“…IPD has been widely used for studying the emergence of cooperation among selfish individuals in a variety of disciplines including artificial intelligence, economics and social sciences, etc. [15]. Table 1.…”

Section: Social Dilemmasmentioning

confidence: 99%

“…Bazzan et al [15] used social attachments (i.e., belonging to a hierarchy or to a coalition) to lead learning agents in a grid to a certain level of cooperation. Although our work solves the same problem, we focus on exploiting emotions in modifying agent behaviors during learning, and do not impose assumptions of hierarchical supervision or coalition affiliation on the agents.…”

Section: Related Workmentioning

confidence: 99%

Emotional Multiagent Reinforcement Learning in Social Dilemmas

Zhang

Ren

2013

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Social dilemmas have attracted extensive interest in multiagent system research in order to study the emergence of cooperative behaviors among selfish agents. Without extra mechanisms or assumptions, directly applying multiagent reinforcement learning in social dilemmas will end up with convergence to the Nash equilibrium of mutual defection among the agents. This paper investigates the importance of emotions in modifying agent learning behaviors in order to achieve cooperation in social dilemmas. Two fundamental variables, individual wellbeing and social fairness, are considered in the appraisal of emotions that are used as intrinsic rewards for learning. Experimental results reveal that different structural relationships between the two appraisal variables can lead to distinct agent behaviors, and under certain circumstances, cooperation can be obtained among the agents.

show abstract

Learning to cooperate in the Iterated Prisoner’s Dilemma by means of social attachments

Cited by 13 publications

References 26 publications

A strategy learning model for autonomous agents based on classification

A strategy learning model for autonomous agents based on classification

A Self-Adaptive Strategy for Evolution of Cooperation in Distributed Networks

Emotional Multiagent Reinforcement Learning in Social Dilemmas

Contact Info

Product

Resources

About