The simulation of societies requires vast amounts of computing resources, which must be managed over distributed or high performance computing infrastructures to provide for cost-effective experimentation. To that end, this paper presents a novel platform for the segmentation and management of social simulation experiments in game-playing multi-agent systems; the platform, also serves as a working proof of concept for similar experiments. The platform is managed through a web-based graphical user interface, to combine the advantages of powerful grid infrastructure middleware and sophisticated workflow systems in a way that some generic functionality is sacrificed for the benefit of obtaining a smooth and brief learning curve, without compromising security. The paper sets out the architecture and implementation details of the platform and demonstrates its use with two sample games, RLGame and Rock Scissors Paper, to underline the scale of the experiments and to indicate the class of social simulation problems that it can help investigate. The platform can be loosely coupled with analytics software for data mining; for our sample problems, this analysis leads to associating the learning mechanism each agent employs with its eventual performance ranking.
FosterI. and KesselmanC., The Grid 2, Second Edition: Blueprint for a New Computing Infrastructure, Morgan Kaufmann, San Francisco, CA, USA, 2003.
2.
RIKEN HPCI Program, for Computational Life Sciences, Largest neuronal network simulation achieved using K computer, http://www.riken.jp/en/pr/press/2013/20130802_1/ (Accessed 2013).
3.
MengistuD., LundbergL. and DavidssonP., Performance prediction of multi-agent based simulation applications on the grid, International Journal of Computer, Information Science and Engineering1(3) (2007).
4.
IngoT.J. and PawlaszczykD., Large scale multiagent simulation on the grid, IEEE International Symposium on Cluster Computing and the Grid (CCGRID), Cardiff University, Cardiff, UK, 2005.
5.
GilbertN. and TroitzschK.G., Simulation for the Social Scientist, 2nd ed, Open University Press, 2005.
6.
RobA.J., Survey of agent based modelling and Simulation Tools, Technical Report, DL-TR-2010-007, 2010.
7.
FerberJ., Multi-agent systems: An introduction to distributed artificial intelligence, Addison-Wesley, 1999.
8.
ShohamY. and LeytonB.K., Multiagent systems: Algorithmic, game-theoretic, and logical foundations, Cambridge University Press, 2009.
9.
MarivateV.N., Social learning methods in board game agents, IEEE Symposium Computational Intelligence and Games, (CIG '08), Perth, Australia, (2008), 323-328.
10.
KiourtC. and KallesD., Social reinforcement learning in game playing, IEEE International Conference on Tools with Artificial Intelligence, Athens, Greece (2012), 322-326.
11.
CaballeroA., BotiaJ. and Gomez-SkarmetaA., Using cognitive agents in social simulations, Engineering Applications of Artificial Intelligence24(7) (2011), 1098-1109.
12.
Al-KhateebB. and KendallG., Introducing a round robin tournament into evolutionary individual and social learning checkers, Developments in E-systems Engineering, Dubai, United Arab Emirates, (2011).
13.
KiourtC. and KallesD., Building a social multi-agent system simulation management toolbox, 6th Balkan Conference in Informatics, Thessaloniki, Greece (2013), 66-70.
14.
EGEE Project, Enabling grids For E-science [ONLINE] http://cordis.europa.eu/projects/rcn/80149_en. html (Accessed 2014), (FP6-INFRASTRUCTURES, 2004).
15.
WittekP. and Rubio-CampilloX., Scalable agent-based modelling with cloud hpc resources for social simulations, IEEE 4th International Conference on Cloud Computing Technology and Science (CloudCom) (2012), 355-362.
16.
PooleD.L. and MackworthA.K., Artificial inteligence: Foundations of computational agents, Cambridge University Press, USA, New York, 2010.
17.
FosterI., ZhaoY., RaicuI. and ShiyongL., Cloud computing and grid computing 360-degree compared, Grid Computing Environments Workshop (2008), 1-10.
18.
SeyyedM.H. and AmidK.B., Cloud computing vs. grid computing, ARPN, Journal of Systems and Software 2.5 (2012), 188-194.
19.
HosamA.H., HamzaA. and TariqA., Comparison between cloud and grid computing: Review paper, International Journal on Cloud Computing: Services and Architecture (IJCCSA)2(4) (2012), 1-21.
20.
GortonI., Cyberinfrastructures: Bridging the divide between scientific research and software engineering, Computer47(8) (2014), 48-55.
21.
CoulourisG., DollimoreJ., KindbergJ. and BlairG., Distributed systems: Concepts and design, Boston: Addison-Wesley, 5th Edition, 2011.
22.
KiourtC. and KallesD., Development of grid-based multi agent systems for social learning, IEEE International Conference on Information Intelligence, Systems and Applications (IISA 2015), Corfu, Greece, (2015).
23.
RailsbackS.F., LytinenS.L. and JacksonS.K., Agent-based simulation platforms: Review and development recommendations, Simulation82(9) (2006), 609-623.
24.
BarbosaJ. and LeitaoP., Simulation of multi-agent manufacturing systems using agent-based modelling platforms, 9th IEEE International Conference on Industrial Informatics, Portugal (2011), 477-482.
25.
CollierN., Repast HPC manual, 6th February, 2012.
26.
DecraeneJ., LeeY.T., ZengF., ChandromohanM., YongY.C. and LowM.Y.H., Evolutionary design of agent-based simulation experiments (demonstration), 10th Int Conf on Autonomous Agents and Multiagent Systems (2011), 1321-1322.
27.
PauloL., UdoI. and Claus-PeterR., Parallelising multi-agent systems for high performance computing, The Third International Conference on Advanced Communications and Computation (INFOCOMP 2013) (2013).
28.
BlanchartE., CambierC., CanapeC., GaudouB., HoT.-N., HoT.-V., LangC., MichelF., MarilleauN. and PhilippeL., EPIS: A grid platform to ease and optimize multi-agent simulators running, Advances on Practical Applications of Agents and Multiagent Systems Advances in Intelligent and Soft Computing88 (2011), 129-134.
29.
CoakleyS., GheorgheM., HolcombeM., ChinS., WorthD. and GreenoughC., Exploitation of high performance computing in the flame agent-based simulation framework, IEEE 14th International Conference on High Performance Computing and Communications (2012), 538-545.
30.
CollierN. and NorthM., Repast HPC: A platform for largescale agent-based modeling, large-scale computing techniques for complex system simulations, John Wiley & Sons, Inc, 2011, pp. 81-110.
31.
DecraeneJ., ChandramohanM., LowM. and ChooC., Evolvable simulations applied to automated red teaming: A preliminary study, in: Proceedings of the 42th Winter Simulation Conference (2010), 1444-1514.
32.
NardinL.G. and SichmanJ.S., Simulating the impact of trust in coalition formation: A preliminary analysis, Advances in Social Simulation, Post-Proceedings of the Brazilian Workshop on Social Simulation (2011), 33-40.
33.
ManzooraU. and ZafarbB., Multi-agent modeling toolkit - MAMT, Simulation Modelling Practice and Theory49 (2014), 215-222.
34.
BauerB., MüllerJ.P. and OdellJ., An extension of uml by protocols for multiagent interaction, proceeding, Fourth International Conference on MultiAgent Systems, ICMAS 2000 Boston, IEEE Computer Society (2000).
35.
BellifemineF., CaireG. and GreenwoodD., Developing multi-agent systems with JADE, Wiley, 2007.
36.
ChenD., TheodoropoulosK.G., TunerJ.S., CaiW., MinsonR. and ZangY., Large scale agent-based simulation on the grid, Journal Future Generation, Computer Systems24(7) (2008), 658-671.
37.
XieY., TeoY.M., CaiW. and TurnerS.J., Service provisioning for HLA-based distributed simulation on the grid, The Nineteenth ACM/IEEE/SCS Workshop on Principles of Advanced and Distributed Simulation, PADS 2005, Monterey, CA, USA, (2005), 282-291.
38.
MinsonR. and TheodoropoulosG., Distributing RePast agent-based simulations with HLA, European Simulation Interoperability Workshop 2004, 04E-SIW-046, (2004).
39.
MarzollaM., FerrettiS. and D'AngeloG., Dynamic resource provisioning for cloud-based gaming infrastructures, Theoretical and Practical Computer Applications in Entertainment10(3) (2012), 1-20.
40.
ChunB.-G., IhmS., ManiatisP., NaikM. and PattiA., CloneCloud: Elastic execution between mobile device and cloud, in: Proc of the 6th European Conference on Computer Systems (EuroSys'11), Salzburg, Austria, ACM, (2011), 301-314.
41.
CuervoE., BalasubramanianA., kiChoD., WolmanA., SaroiuS., ChandraR. and BahlP., MAUI: Making smartphones last longer with code offload, in: Proc of the 8th International Conference on Mobile Systems, Applications, and Services (MobiSys'10), San Francisco, California, ACMUSA., (2010), 49-62.
42.
ChessD., HarrisonC. and KershenbaumA., Mobile agents: Are they a good idea? in: Mobile Object Systems Towards the Programmable Internet1222 (2005).
43.
ChenJ., HanX. and JiangG., A negotiation model based on multi-agent system under cloud computing, The Ninth International Multi-Conference on Computing in the Global Information Technology, Seville, Spain, (2014), 157-164.
44.
SiddiquiU., TahirG.A., RehmanA.U., AliZ., RasoolR.U. and BloodsworthP., Elastic JADE: Dynamically scalable multi agents using cloud resources, Second International Conference in Cloud and Green Computing (CGC), (2012), 167-172.
45.
Al-AyyoubM., JararwehY., DaraghmehM. and AlthebyanQ., Multi-agent based dynamic resource provisioning and monitoring for cloud computing systems infrastructure, Journal Cluster Computing18(2) (2015), 919-932.
46.
LittmanL.M., Markov games as a framework for multi-agent reinforcement learning, Eleventh International Conference on Machine Learning (1994), 157-163.
47.
KallesD. and KanellopoulosP., On verifying game design and playing strategies using reinforcement learning, Proceedings of ACM Symposium on Applied Computing, special track on Artificial Intelligence and Computation Logic, Las Vegas (2001).
48.
FariasV.F., MoallemiC.C., Van RoyB. and WeissmanT., Universal reinforcement learning, IEEE Transactions on Information Theory56(5) (2010), 2441-2454.
49.
BillingsD., Thoughts on RoShamBo, ICGA Journal23(1) (2000), 3-8.
50.
SuttonR. and BartoA., Reinforcement learning - an introduction, MIT Press, Cambridge, MA, 1998.
51.
MarchJ.G., Exploration and exploitation in organizational learning, Organization Science2(1) (1991), 71-87.
52.
SuttonR., Learning to predict by the methods of temporal differences, Machine Learning3(1) (1988), 9-44.
53.
ShannonC., Programming a computer for playing chess, Philosophical Magazine41(4) (1950), 265-275.
54.
SamuelA., Some studies in machine learning using the game of checkers, IBM Journal of Research and Development, (1959), 210-229.
55.
HsuF.H., Behind deep blue: Building the computer that defeated the world chess champion, Princeton University Press, 2002.
56.
SchaefferJ., BjoernssonY., BurchN., KishimotoA., MuellerM., LakeR., LuP. and SutphenS., Checkers is solved, Science317(5844), (2007), 1518-1522.
57.
TesauroG., Temporal difference learning and TD-gammon, Communications of the ACM38(3) (1995), 58-68.
58.
LebanG., ZupanB., VidmarG. and BratkoI., VizRank: Data visualization guided by ma-chine learning, Data Mining and Knowledge Discovery13(2) (2006), 119-136.
59.
GeorgasA., KallesD. and TatsisV.A., Scientific workflows for game analytics, in: Encyclopedia of Business Analytics and Optimization, WangJ., ed., 2014, pp. 2115-2125.
