The dynamics of reinforcement social learning in networked cooperative multiagent systems

Cooperative Multi-Agent Learning in Social Networks: A Review

“…Hao and Leung [5] investigated the multi-agent coordination problem by proposing two types of learners (IALs and JALs) in cooperative environments under the social learning framework, which was complementary to the large body of previous work in the framework of repeated interactions among fixed agents. The learning performance of both types learners was evaluated by authors by using a number of rigorous cooperative games, and the resulting influence of the degree of information sharing degree upon the performance of learning and reasoning was analyzed as well.…”

“…Initially, no underlying topology was considered in the social learning framework, which thus could not fully reflect the interaction in practical multi-agent systems. So, to make the coordination techniques applicable in practice especially for those MAS applications closely residing in existing social networks, Hao et al [9] considered the underlying topologies of interaction environment when designing coordination techniques. Our research direction is to consider utilizing the characteristics of different neighboring agents (e.g., the relative degree of nodes in the neighborhood, the past interaction histories of different nodes) when performing the multi-agent learning to improve coordination performance.…”

“…Hao et al [9] carried out a systematic investigation about how agents could effectively learn so as to coordinate on an optimal policy in various cooperative multi-agent environments under the networked social learning framework. In their framework, they proposed two types of learners: IALs and JALs.…”

Norm emergence in multiagent systems: a viewpoint paper

“…Norm emergence or convergence is widely accepted to have happened, or a norm is said to have emerged, when a predetermined percentage of the population observes the Balaraman and Singh [13] Beheshti and Sukthankar [16] Beheshti et al [17] Bench-Capon and Modgil [18] Boissier et al [22] Boella and van der Torre [20] Boella and van der Torre [19] Boyd and Richerson [23] Broersen et al [24] Brooks et al [25] Campos et al [26] Chakrabarti and Basu [28] Chao Yu et al [29] Cliffe et al [31] Conte and Castelfranchi [32] Criado et al [35] Dascalu et al [37] Dastani and van der Torre [38] dos Santos Neto et al [41] Franks et al [42] Frantz et al [43] Ghorbani et al [48] Ghorbani and Bravo [46] Hoffmann [55] Hofmann et al [56] Hassani-Mahmooei and Parris [53] Hao and Leung [49] Hao et al [50] Hao et al [51] Hao et al [52] Hu and Leung [57] Hübner et al [58] Lopez [65] Lotzmann et al [66] Lee et al [61] Mahmoud et al [67] Mashayekhi et al [68] Mukherjee et al [75] Mungovan et al [76] Morales et al [70] Morales et al [72] Morales et al [71] Mor...…”

An Optimal Rewiring Strategy for Cooperative Multiagent Social Learning

“…Until now, a lot of works have studied the multiagent coordination problems in cooperative MASs (Claus and Boutilier 1998). One class of research is multiagent social learning (Sen and Airiau 2007), which study the multiagent coordination problem among a population of cooperative agents with sparse and local interactions (Hao and Leung 2013).…”