Social or Individual Learning? An Aggregated Solution for Coordination in Multiagent Systems
- 28 Downloads
There are mainly two different ways of learning for animals and humans: trying on yourself through interactions or imitating/copying others through communication/observation. How these two learning strategies differ and what roles they are playing in achieving coordination among individuals are two challenging problems for researchers from various disciplines. In multiagent systems, most existing work simply focuses on individual learning for achieving coordination among agents. The social learning perspective has been largely neglected. Against this background, this article contributes by proposing an integrated solution to decision making between social learning and individual learning in multiagent systems. Two integration modes have been proposed that enable agents to choose in between these two learning strategies, either in a fixed or in an adaptive manner. Experimental evaluations have shown that these two kinds of leaning strategies have different roles in maintaining efficient coordination among agents. These differences can reveal some significant insights into the manipulation and control of agent behaviors in multiagent systems, and also shed light on understanding the social factors in shaping coordinated behaviors in humans and animals.
KeywordsIndividual learning social learning coordination multiagent systems
Unable to display preview. Download preview PDF.
This work is supported by the NationalNatural Science Foundation of China under Grant 61771089, 61502072, 61572104 and 61403059, Fundamental Research Funds for the Central Universities of China under Grant DUT16RC(4)17, and Post-Doctoral Science Foundation of China under Grants 2014M561229 and 2015T80251.
- Hegselmann R., Krause U. et al. (2002). Opinion dynamics and bounded confidence models, analysis, and simulation. Journal of artificial societies and social simulation, 5(3): 1–33.Google Scholar
- Hofmann L., Chakraborty N., and Sycara K. (2011). The evolution of cooperation in self-interested agent societies: a critical study. In Proc. of 10th AAMAS, pp. 685–692, Toronto, Canada, May 10-14, 2011.Google Scholar
- Mukherjee P., Sen S., and Airiau S. (2008). Norm emergence under constrained interactions in diverse societies. In Proc. of 7th AAMAS, pp. 779–786, Estoril, Portugal, May 12-16, 2008.Google Scholar
- Sen S. and Airiau S. (2007). Emergence of norms through social learning. In Proc. of 20th IJCAI, pp. 1507–1512, Hyderabad, India, January 6-12, 2007.Google Scholar
- Shibusawa R. and Sugawara T. (2014). Norm emergence via influential weight propagation in complex networks. In Network Intelligence Conference (ENIC), 2014 European. IEEE, pp. 30–37, Wroclaw, Poland, September 29-30, 2014.Google Scholar
- Villatoro D., Sabater-Mir J., and Sen S. (2011). Social instruments for robust convention emergence. In Proc. of 22nd IJCAI, pp. 420–425, Barcelona, Catalonia, Spain, July 16-22, 2011, AAAI Press.Google Scholar
- Villatoro D., Sen S., and Sabater-Mir J. (2009). Topology and memory effect on convention emergence. In Proc. of WIIAT’09, pp. 233–240, Milan, Italy, September 15-18, 2009.Google Scholar
- Yu C., Lv H., Sen S., Hao J., Ren F., and Liu R. (2016). An adaptive learning framework for efficient emergence of social norms: (extended abstract). In International Conference on Autonomous Agents Multiagent Systems, pp. 1307–1308, Singapore, May 9-13, 2016.Google Scholar
- Yu C., Liu R., and Wang Y. (2016). Social learning in networked agent societies. In IEEE International Conference on Agents, pp. 57–62, Matsue, Japan, September 28-30, 2016.Google Scholar
- Yu C., Lv H., Ren F., Bao H., and Hao J. (2015). Hierarchical learning for emergence of social norms in networked multiagent systems. In Australasian Joint Conference on Artificial Intelligence. pp. 630–643, Canberrra, Australia, Nov. 30-Dec. 4, 2015, Springer.Google Scholar
- Yu C., Lv H., Sen S., Ren F., and Tan G. (2016). Adaptive learning for efficient emergence of social norms in networked multiagent systems. In Pacific Rim International Conference on Trends in Artificial Intelligence, pp. 805–818, Phuket, Thailand, August 22-26, 2016.Google Scholar
- Yu C., Y. Chen, Lv H., Ren J., Ge H., and Sun L. (2017). Neural learning for the emergence of social norms in multiagent systems. In IEEE International Conference on Agents, pp. 40–45, Beijing, China, July 6-9, 2017.Google Scholar
- Yu C., Zhang M., Ren F., and Luo X. (2013). Emergence of social norms through collective learning in networked agent societies. In Proc. of AAMAS2013, pp. 475–482, Saint Paul, USA, May 6-10, 2013.Google Scholar
- Yu C., Zhang M., and Ren F. (2013). Emotional multiagent reinforcement learning in social dilemmas. In International Conference on Principles and Practice of Multi-Agent Systems, pp. 372–387, Dunedin, New Zealand, December 1-6, 2013.Google Scholar