Abstract
This paper presents an evolutionary approach that, given a performance goal, produces a communication strategy that can improve a multi-agent system’s performance with respect to the desired goal. The evolved strategy determines what, when, and to whom agents communicate. The proposed approach further enables tuning the trade-off between the performance goal and communication cost, to produce a strategy that achieves a good balance between the two objectives, according the system’s designer needs. Experiments are designed to evaluate the approach using the Wumpus World application domain, with variations of three factors: fitness parameters (including objectives’ weights and action and communication costs), fitness goal, and simulation environment. Results show that the system’s performance can be highly tuned by controlling communication, and that the presented approach has significant utilization in improving the performance with respect to the goal.
Similar content being viewed by others
References
Althnian A, Agah A (2015) Evolutionary learning of goal-oriented communication strategies in multi-agent systems. J Autom Mob Robot Intell Syst 9:52–64. doi:10.14313/JAMRIS_3-2015/24
Balch T, Arkin RC (1994) Communication in reactive multiagent robotic systems. Auton Robot 1:27–52. doi:10.1007/BF00735341
Becker R, Carlin A, Lesser V, Zilberstein S (2009) Analyzing myopic approaches for multi-agent communication. Comput Intell 25:31–50. doi:10.1111/j.1467-8640.2008.01329
Bussink D (2004) A comparison of language evolution and communication protocols in multi-agent systems. In: 1st twente student conference on IT. doi:10.3990/10.1.1.76.3051
Cangelosi A (1999) Modeling the evolution of communication: from stimulus associations to grounded symbolic associations. Adv Artif Life. doi:10.1007/3-540-48304-7_86
Cangelosi A (2001) Evolution of communication and language using signals, symbols, and words. IEEE Trans Evol Comput 5(2):93–101. doi:10.1109/4235.918429
Carlin A, Zilberstein S (2009) Myopic and non-myopic communication under partial observability. Web Intell Intell Agent Technol 2:331–338. doi:10.1109/WI-IAT.2009.174
Chakraborty D, Sen S (2007) Computing effective communication policies in multiagent systems. In: Proceedings of the 6th international joint conference on autonomous agents and multiagent systems. doi:10.1145/1329125.1329168
Conforth M, Meng Y (2008) Communication scheme comparison for a distributed multi-agent system. Proc Int Conf Artif Intell 2:106–112
De Greeff J, Nolfi S (2010) Evolution of implicit and explicit communication in mobile robots. Evol Commun Lang Embodied Agents. doi:10.1007/978-3-642-01250-1_11
Dutta P, Goldman C, Jennings N (2007) Communicating effectively in resource-constrained multi-agent systems. Int Jt Conf Artif Intell 20:1269–1274
Floreano D, Mitri S, Magnenat S, Keller L (2007) Evolutionary conditions for the emergence of communication in robots. Curr Biol 17(6):514–519
Galantucci B, Steels L (2008) The emergence of embodied communication in artificial agents and humans. In: Wachsmuth I, Lenzen M, Knoblich G (eds) Embodied Communication in Humans and Machines. Oxford University Press, Oxford
Ghavamzadeh M, Mahadevan S (2004) Learning to communicate and act using hierarchical reinforcement learning. In: Proceedings of the third international joint conference on autonomous agents and multiagent systems, vol 3, pp 1114–1121
Giles CL, Jim KC (2000) Talking helps: evolving communicating agents for the predator-prey pursuit problem. Artif Life 6:237–254. doi:10.1162/106454600568861
Goldman CV, Zilberstein S (2003) Optimizing information exchange in cooperative multi-agent systems. In: Proceedings of the second international joint conference on autonomous agents and multiagent systems, pp 137–144. doi:10.1145/860575.860598
Holland JH (1975) Adaptation in natural and artificial systems: an introductory analysis with applications to biology, control, and artificial intelligence. Unversity of Michigan Press, Michigan
Howard RA (1966) Information value theory. IEEE Trans Syst Sci Cybern 2:22–26. doi:10.1109/TSSC.1966.300074
Hurt D, Tarau P (2005) An empirical evaluation of communication effectiveness in autonomous reactive multiagent systems. In: Proceedings of the 2005 ACM symposium on applied computing, pp 74–78. doi:10.1145/1066677.1066698
Iba H, Nozoe T, Ueda K (1997) Evolving communicating agents based on genetic programming. IEEE Int Conf Evol Comput. doi:10.1109/ICEC.1997.592321
Iba H (1998) Evolutionary learning of communicating agents. Inf Sci 108:181–205. doi:10.1016/S0020-0255(97)10055-X
Kinney M, Tsatsoulis C (1998) Learning communication strategies in multiagent systems. Appl Intell 9:71–91. doi:10.1023/A:1008251315338
Mackin KJ, Tazaki E (2000) Unsupervised training of multiobjective agent communication using genetic programming. In: Proceedings of fourth international conference on knowledge-based intelligent engineering systems and allied technologies, vol 2, pp 738–741. doi:10.1109/KES.2000.884152
Mackin KJ, Tazaki E (2002) Multi-agent communication combining genetic programming and pheromone communication. Kybernetes 31:827–843. doi:10.1108/03684920210432808
MacLennan B (1990) Evolution of communication in a population of simple machines. doi:10.7290/10.1.1.33.5379
Marocco D, Cangelosi A, Nolfi S (2003) The emergence of communication in evolutionary robots. Philos Trans R Soc Lond A Math Phys Eng Sci 361(1811):2397–2421
Marocco D, Nolfi S (2006) Origins of communication in evolving robots. Anim Animat 9:789–803. doi:10.1007/11840541_65
Marocco D, Nolfi S (2006) Self-organization of communication in evolving robots. Proc Conf Artif Life (ALIFE). doi:10.1162/10.1.1.80.6069
Marocco D, Nolfi S (2005) Emergence of communication in embodied agents evolved for the ability to solve a collective navigation problem. Connect Sci 19(1):53–74. doi:10.1080/09540090601015067
Mataric M (1995) Communication strategies for cooperating behaviour-based robots. AAAI Technical report
Melo FS, Spaan MT (2011) A POMDP-based model for optimizing communication in multiagent systems. In: Proceedings of 1st European workshop on multiagent systems
Nair R, Roth M, Yohoo M (2004) Communication for improving policy computation in distributed POMDPs. In: Proceedings of the third international joint conference on autonomous agents and multiagent systems, vol 3, pp 1098–1105. doi:10.1109/AAMAS.2004.88
Nolfi S (2005) Emergence of communication in embodied agents: co-adapting communicative and non-communicative behaviours. Connect Sci 17(3–4):231–248. doi:10.1080/09540090500177554
Nolfi S (2013) Emergence of communication and language in evolving robots. New Perspect Orig Lang 144:533–554. doi:10.1075/slcs.144.20nol
Nolfi S, Mirolli M (2009) Evolution of communication and language in embodied agents. Springer Science and Business Media, New York
North MJ, Howe TR, Collier N, Vos JR (2005) The repast simphony runtime system. In: Proceedings of the agent 2005 conference on generative social processes, models, and mechanisms
Preist C, Pearson S (1998) An adaptive choice of messaging protocol in multi-agent systems. Proc Int Conf Multi Agent Syst. doi:10.1109/ICMAS.1998.699284
Quinn M (2001) Evolving communication without dedicated communication channels. Adv Artif Life. doi:10.1007/3-540-44811-X_38
Rawal A, Rajagopalan P, Miikkulainen R, Holekamp K (2012) Evolution of a communication code in cooperative tasks. Int Conf Simul Synth Living Syst 13:243–250. doi:10.7551/978-0-262-31050-5-ch033
Roth M (2007) Execution-time communication decisions for coordination of multi-agent teams. Dissertation, Carnegie Mellon University
Russell S, Norvig P (1995) Artificial Intelligence: a modern approach. Prentice-Hall, New jersey
Steels L (2003) The evolution of communication systems by adaptive agents. Adapt Agent Multi-Agent Syst. doi:10.1007/3-540-44826-8_8
Steels L (2003) Evolving grounded communication for robots. Trends Cognit Sci 7(7):308–312. doi:10.1016/S1364-6613(03)00129-3
Steels L (2015) The talking heads experiment: origins of words and meanings. Comput Models Lang Evol
Steels L, Bleys J (2005) Planning what to say: second order semantics for fluid construction grammars. Proc CAEPIA. doi:10.1007/10.1.1.80.9026
Thierens D (1998) Selection schemes, elitist recombination, and selection intensity. In: Proceedings of the 7th international conference on genetic algorithms, 152–159. doi:10.1.1.19.236
Tian L, Luo J, Huang Z (2013) Communication based on interactive dynamic influence diagrams in cooperative multi-agent systems. In: Proceedings of 8th international conference on computer science and education, pp 56–61. doi:10.1109/ICCSE.2013.6553883
Trianni V, Labella TH, Dorigo M (2004) Evolution of direct communication for a swarm-bot performing hole avoidance. Ant Colony Optim Swarm Intell. doi:10.1007/978-3-540-28646-2_12
Wei C, Hindricks K, Jonker CM (2014) The role of communication in coordination protocols for cooperative robot teams. Int Conf Agents Artif Intell. doi:10.5220/0004758700280039
Werner G M, Dyer M (1991) Evolution of communication in artificial organisms. In: Proceedings of the second international conference of artificial life, pp 659–687
Williamson S, Gerding E, Jennings N (2008) A principled information valuation for communications during multi-agent coordination. AAMAS workshop on multi-agent sequential decision making in uncertain domains, pp 137–151
Wischmann S, Floreano D, Keller L (2012) Historical contingency affects signaling strategies and competitive abilities in evolving populations of simulated robots. Proc Natl Acad Sci 109(3):864–868
Wu AS, Yu H, Jin S, Lin KC, Schiavone G (2004) An incremental genetic algorithm approach to multiprocessor scheduling. IEEE Trans Parallel Distrib Syst 15:824–834. doi:10.1109/TPDS.2004.38
Wu F, Zilberstein S, Chen X (2011) Online planning for multi-agent systems with bounded communication. Artif Intell 175:487–511. doi:10.1016/j.artint.2010.09.008
Zhang Y (2006) Observant and proactive communication in multi-agent teamwork. Int Conf Intell Agent Technol. doi:10.1109/IAT.2006.97
Acknowledgments
A. Althnian would like to thank King Saud University for the scholarship support.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Althnian, A., Agah, A. Evolving goal-driven multi-agent communication: what, when, and to whom. Evol. Intel. 9, 181–202 (2016). https://doi.org/10.1007/s12065-016-0137-2
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12065-016-0137-2