`
`Designing a Massively Multiplayer Online Game / Research Testbed
`Featuring AI-Driven NPC Communities
`
`Michael Zyda, Marc Spraragen, Balakrishnan Ranganathan, Bjarni Arnason,
`Peter Landwehr
`
`University of Southern California GamePipe Laboratory
`Carnegie Mellon University CASOS Group
`{zyda, sprarage, brangana, barnason}@usc.edu
`plandweh@cs.cmu.edu
`
`Abstract
`Massively Multiplayer Online Games (MMOGs), in their aspect
`as online communities, represent an exciting opportunity for
`studying social and behavioral models. For that purpose we
`have developed Cosmopolis, a free MMOG containing several
`key research-oriented features. First, Cosmopolis consists of an
`outer game for larger-scale social modeling, as well as a set of
`subgames
`suitable
`for
`tightly-controlled
`sandbox-style
`experiments, all allowing a high
`level of data
`logging
`configuration and control by researchers. Also, Cosmopolis’s
`world model incorporates configurable, AI-driven non-player
`character communities, as a means of researching interactions
`between individuals and societies.
`
`Objective and Motivation
`A 2008 study by the National Research Council entitled
`“Behavioral Modeling and Simulation – from Individuals
`to Societies” [NRC 2008] discusses how we need to
`expand research in modeling and simulation to include
`models of individual and societal behaviors, both human
`and AI (and hybrid). In the study, it is pointed out that a
`technological infrastructure needs to be developed for
`behavioral modeling such that we can properly develop,
`test and then deploy such models. The study, in fact,
`suggests the development of a massively multiplayer
`online game (MMOG) for that infrastructure. Such an
`MMOG can be utilized as a test bed for models of
`individual and group phenomena.
`Cosmopolis is an MMOG we are developing for
`this purpose. In designing the game, we have been
`motivated by the need to balance the diverse interests of
`players and researchers: players need a fun game
`experience, while researchers need the flexibility to
`perform various experiments of their own design. To
`accomplish these goals, we’ve designed the game to
`incorporate specific features to work towards these ends.
`________________________
`Copyright © 2010, Association for the Advancement of Artificial
`Intelligence (www.aaai.org). All rights reserved.
`
`Cosmopolis is centered on a world-building outer
`game and a collection of self-contained sub-games of any
`genre (action, puzzles, sports, etc.). Cosmopolis also
`contains a new approach to incorporating information
`channels into a game environment: dissemination of both
`in-game messages and real-world feeds [Zyda et al.
`2010]. Previous virtual environments and their AI-based
`denizens do not have the ability to analyze information
`feeds from real-world events. We believe this ability is an
`important factor for effective simulation of virtualized
`social and organizational environments.
`For researchers, Cosmopolis is a unique test bed
`and data source for studying social and behavioral
`models. These models can be of individual players or
`multiple players over time, as well as of non-player
`characters (NPCs), or combinations of those. The game
`provides various and flexible methods to facilitate these
`needs. These methods include administrator-produced in-
`game events (natural disasters, etc.), specifically designed
`and instantiated experiments in subgames, and AI-driven
`NPC communities featuring customized cultural models.
`
`Method
`The first subsection below discusses Cosmopolis in terms
`of its game design features for players, as influenced by
`the MMOG design guidelines mentioned
`in
`the
`background section. Key features covered include the
`outer game / subgame structure, and the game world’s
`information channel system with its novel inclusion of
`real-world newsfeeds and its effects.
` The second
`subsection describes the design features of Cosmopolis as
`a research
`testbed.
` Both subsections
`incorporate
`examination of the engineering criteria used to build
`Cosmopolis, and a discussion of some ways in which AI
`NPC communities are incorporated into the world model.
`
`108
`
`Niantic's Exhibit No. 1044
`Page 001
`
`
`
`1. Game design
`
`As a game, Cosmopolis has a two-level structure: outer
`game and subgames. The outer game is a present-day
`city- and world-building simulation, including player-
`level and guild-level conflicts. The various subgames will
`be housed in any buildings or areas in the world. This
`two-level format supports our aim of attracting as many
`players and player
`types as possible, consequently
`yielding data about a wide variety of individuals in
`distinct populations and about the relations among them.
`Currently,
`there are
`three completed or
`developing 3D subgames
`in Cosmopolis: WarPipe,
`Operation:Peace, and DungeonRun. WarPipe
`is a
`multiplayer action/shooter game for individuals or teams,
`featuring a detailed urban battleground and 1st/3rd person
`camera perspectives.
` Operation:Peace, a simulation
`designed for the United Nations Millennium Challenge,
`involves social interactions between players and NPCs in
`a demilitarized zone. DungeonRun is a single-player
`fantasy-themed action/adventure game with AI-controlled
`monsters.
`In terms of engineering, Cosmopolis is designed
`to be an engaging game, with state-of-the-art graphics and
`effects. The game engine has been built from the ground
`up with the primary objective of supporting a massive,
`changing world seamlessly. By design, Cosmopolis needs
`to be able to support large cities and wilderness in
`addition to providing a cohesive experience across the
`subgames and the outer game. For example, the current
`game world has a total area of 8 km2, and supports
`importing real world height data to recreate small islands,
`etc.
`
`All of the action in Cosmopolis is handled by an
`event-based networking model. Each event has certain
`properties that define how it will be perceived in the
`subgame and the outer game. This approach enables us to
`be flexible with regards to the level of interconnectedness
`between the subgame and the outer game as desired by
`the researchers and game designers. Subgames could be
`designed
`to be completely
`isolated sandboxes
`like
`MMOG instances (like the DungeonRun subgame) or be
`seamlessly integrated with the outer game (like the
`Operation:
`Peace
`region-based
`subgame
`or
`a
`neighborhood basketball court). This system is also data-
`driven so designers can tweak the various parameters
`without having to ask the engineers to rebuild the game
`for each tweak. This also reduces the burden on the
`subgame engineers as they need not worry about the
`integration with the outer world for components like
`particle systems, sound, character movement and
`animation, etc.
`In Cosmopolis, the in-game information system
`is a collection of channels through which messages flow.
`Channels may display news feeds from the real world or
`commercial advertisements; channels may publish in-
`
`game announcements publicly or regionally; channels
`may be configured as special chat lines between players.
`We aim to present messages efficiently and effectively to
`and between players, as well as to support the framework
`for the study of information spread and analysis.
`For example, Cosmopolis features an in-game
`virtual economy system that has a commodity market and
`currency exchange market. All the commodity prices and
`currency exchange rates are synchronized periodically
`with
`incoming
`real-world
`rates. Using processing
`techniques such as keyword searches, Cosmopolis can
`extract data from information channels that may change
`the behaviors of NPCs (implemented as AI-driven
`software agents). Warnings of “terrorist attack” or
`“earthquake danger” may cause NPCs to flee an area.
`Rumors of “unrest” may coincide with NPCs behaving in
`a less friendly manner towards players or each other.
`Stock market gradients can also change the personalities
`of the NPCs, e.g. increasing indices make them happier,
`and decreasing indices make them nervous.
`As Cosmopolis’s information system is relatively
`untested, it is an open question as to all the ways it will
`affect players. However, some speculation is possible.
`Players may be influenced by the game world’s or NPCs’
`responses to certain events as described above. For
`example, NPCs are programmed to respond to earthquake
`predictions in a certain manner, and the players can learn
`from NPCs’ actions. Another example is that players
`may choose to move to a region where commodities are
`becoming relatively more valuable. Also, there may be
`information channels that show players certain data (such
`as social networks) from the game, to see if providing
`such information alters player behavior.
`
`2. Research testbed design
`
`As a research testbed, Cosmopolis offers a critical degree
`of experimental flexibility beyond
`the data-logging
`capability of the standard MMOG. Our overall design
`comprises a federated model architecture: each subgame
`is a potential lab for a different social and behavioral
`model, maintaining interoperability with the outer game
`world model. Subgames may be added, gameplay of the
`outer world can be tweaked, and different NPC cultures
`and communities may appear, all to meet the needs of
`researchers who use our game to validate or collect data
`for their models. While all in-game events will be logged,
`we will be specifically providing appropriate data export,
`reporting,
`and visualization
`capabilities
`so
`that
`researchers can easily analyze the experiments that they
`design and conduct in the game environment. Exported
`data would include player and NPC characteristics and
`activities,
`relational
`information
`such
`as who
`communicated with whom, performance outcomes, geo-
`temporal activity sequences and so on.
`
`109
`
`Niantic's Exhibit No. 1044
`Page 002
`
`
`
`From an engineering standpoint, the subgames’
`content and logic is completely isolated from the outer
`game except for a controlled data access pipeline. This
`enables administrators and researchers to set exactly what
`part of the outer world this subgame can modify, to
`prevent any unexpected behavior. This also means that in
`the event of any bug or design inconsistencies in any of
`the subgames, it can safely be taken down without
`affecting the rest of the game.
`The event-based networking model enables
`logging management, which
`is vital
`for
`efficient
`researchers using Cosmopolis as a data source. The
`logging parameters can vary among players, NPCs, and
`subgames, based on the needs of different researchers.
`The current networking model has separate gameplay and
`analysis servers. The analysis server can be tasked to
`perform near real-time processing in addition to logging
`the data.
`the account management from
`To separate
`gameplay logic, Cosmopolis uses web services to perform
`authentication and initiate game connection. This also
`paves the way for enabling researchers to control different
`parameters of the game from the browser. For example,
`they could add buildings, move objects, change the
`weather, or alter the default friendliness of an NPC
`community towards outsiders.
`One experiment in progress, based on the
`of
`knowledge
`dissemination,
`involves
`concept
`communities of NPCs in Cosmopolis’ Operation: Peace
`subgame. Facts and beliefs will be spread through NPC
`communication networks of various configurations. One
`set of the social network configuration parameters is the
`physical
`layout of
`the NPCs and
`their walking
`routes/speeds. Another set of parameters will determine
`how trusting the community is of information introduced
`by a player character or a newsfeed. In other words, how
`far and with what degree of confidence would such
`information spread, and how would belief/disbelief of that
`information affect the NPCs’ behavior?
`
`Discussion
`MMOGs are widespread and popular online communities;
`World of Warcraft alone boasts millions of player
`characters.
` The significance of Cosmopolis is its
`uniqueness as an MMOG designed specifically as a
`research testbed for social and behavioral models, with a
`correspondingly high degree of researcher control over
`experiments performed in and data gleaned from the game
`world. A few of the key features that Cosmopolis
`incorporates are a system of nested subgames, a world-
`development mechanic, a channel-based
`information
`system, and interactive AI communities. While these
`features help to make the game novel and fun, they also
`have specific applications for scientists opting to use
`
`Cosmopolis as a research platform: subgames are a way
`for researchers to conduct isolated experiments; the
`modifiable nature of the world allows for events to occur
`that may dramatically alter the main game environment,
`providing fodder for scientists interested in the evolution
`of online communities; the information broadcasting
`systems will allow different messages to be broadcast to
`different portions of the community to help manage
`experiments conducted on the entire player community;
`and, configurable communities of NPCs allow for
`validation of various social and behavioral models
`involving AI principles and techniques. Furthermore,
`ready access to a high-fidelity data set means that
`researchers will have an easier time determining the
`impacts of different treatments on the community in
`Cosmopolis than do researchers of more closed gaming
`environments. Also, all Cosmopolis interactions are
`eminently documentable, and may be used to explore the
`mappings between game world and real world societies.
`It is impossible for one MMOG to be considered
`the definitive online game, and Cosmopolis is not
`intended to be that. But it is an important step in opening
`up game environments for use by researchers, and one
`that will help support the work of many scientists
`interested in studying game environments and how
`different phenomena manifest within them. At present we
`are designing and running our own first experiments
`within Cosmopolis. We hope that the demonstration of the
`feasibility of Cosmopolis will encourage other researchers
`to look to game environments -either Cosmopolis or their
`own more specialized platforms- as avenues for research
`into human and AI character-based interaction.
`
`Bio
`Michael Zyda is the Founding Director of the USC
`GamePipe Laboratory, and a Professor of Engineering
`Practice in the USC Department of Computer Science. At
`the USC Viterbi School of Engineering, he founded the
`Games
`cross-disciplinary
`degree
`programs
`and
`dramatically
`increased
`the
`incoming undergraduate
`enrollment of the Computer Science Department. From
`Fall 2000 to Fall 2004, he was the Founding Director of
`the MOVES Institute located at the Naval Postgraduate
`School, Monterey and a Professor in the Department of
`Computer Science at NPS as well. From 1986 until the
`formation of the MOVES Institute, he was the Director of
`the NPSNET Research Group. Professor Zyda's research
`interests
`include
`computer
`graphics,
`large-scale,
`networked 3D virtual
`environments,
`agent-based
`simulation, modeling human and organizational behavior,
`interactive computer-generated story, computer-generated
`characters, video production,
`entertainment/defense
`collaboration, modeling and simulation, and serious and
`entertainment games. He is a pioneer in the following
`
`110
`
`Niantic's Exhibit No. 1044
`Page 003
`
`
`
`fields - computer graphics, networked virtual reality,
`modeling and simulation, and serious and entertainment
`games. He holds a lifetime appointment as a National
`Associate of the National Academies, an appointment
`made by the Council of the National Academy of
`Sciences in November 2003, awarded in recognition of
`“extraordinary service” to the National Academies. He is
`a member of the Academy of Interactive Arts & Sciences.
`He served as the principal investigator and development
`director of the America’s Army PC game funded by the
`Assistant Secretary of the Army for Manpower and
`Reserve Affairs. He
`took America’s Army
`from
`conception to three million plus registered players and
`hence, transformed Army recruiting. The creation of the
`America’s Army game founded the serious games field.
`
`References
`
`National Research Council. Behavioral Modeling and
`Simulation: from Individuals to Societies, Committee
`on Human Factors, Division of Behavioral and Social
`Sciences and Education, National Research Council,
`National Academies Press, Washington, DC, 2008,
`ISBN 0-309-11862-X.
`
`Zyda, M., Spraragen, M., Ranganathan, B., Arnason, B.,
`and H. Liu.
` Information Channels in MMOGs:
`Implementation and Effects. To appear in proceedings
`of AHFE 2010, Miami, FL.
`
`111
`
`Niantic's Exhibit No. 1044
`Page 004
`
`