DOCSLIB.ORG

Intelligent Agent Concepts in the Modern Library

Total Page：16

File Type：pdf, Size：1020Kb

Download full-text PDF Read full-text
Intelligent Agent Concepts in the Modern Library Please do not remove this page Intelligent Agent Concepts in the Modern Library Dent, Valeda https://scholarship.libraries.rutgers.edu/discovery/delivery/01RUT_INST:ResearchRepository/12643389390004646?l#13643533210004646 Dent, V. (2007). Intelligent Agent Concepts in the Modern Library. In Library Hi Tech (Vol. 25, Issue 1, pp. 108–125). Rutgers University. https://doi.org/10.7282/T3B56H29 This work is protected by copyright. You are free to use this resource, with proper attribution, for research and educational purposes. Other uses, such as reproduction or publication, may require the permission of the copyright holder. Downloaded On 2021/09/30 23:21:33 -0400 Intelligent Agent Concepts in the Modern Library Valeda F. Dent Introduction Agent technology, a sub-field of artificial intelligence, is not a new concept. The idea of the intelligent agent was first introduced by John McCarthy in the mid-1950s, while at MIT. Bradshaw (1997) suggests that it was not until after World War II that the forerunners of the software agent began to emerge. Norman (1997) advances that the “most relevant” predecessors of software agents were things like factory control devices, and automatons that controlled the takeoff, landing and piloting of aircraft. Lewis suggested in 1996 that a shift away from the network operating system to Internet-based network computing was taking place. If true, we are now ten years into this shift, perhaps approaching the tail-end of it. There is no doubt that the advent of the Internet has fueled discussion about the use of agent technology, and supported subsequent implementation on a much broader scale. The popularity of agent technology has increased, decreased and increased again over the past few decades (as the wave of professional literature published during the mid 1980s and 1990s indicates), and a number of researchers proclaimed the future belonged to agents, “Agents will be the most important computing paradigm in the next ten years…By the year 2000, every significant application will have some form of agent-enablement” (Janca, 1996). While this has not transpired, many researchers still believe that the technology is here to stay. One of the earliest intelligent agents was called ELIZA, created in 1966 at MIT by Joseph Weizenbaum, to simulate a conversation with a physiotherapist. ELIZA used natural language to communicate with the user, and her software code included only 240 lines. Today’s agents are incredibly flexible software components, used in complex systems such as traffic management and route guidance (Adler, Satapathy, Manikonda, Bowles and Blue, 2005), power grid system control (Flynn and Dodd, 2006), and supply chain management (Xue, Xiaodong, Qiping, and Wang, 2005). One area of intense and ongoing debate is the definition of agents. There are numerous definitions of what an intelligent agent is, and just as many that focus on what an agent is not. 1 There is also rigorous debate about the concept of the truly intelligent agent, whether it exists, or can be designed. In his compilation of essays on agent technology, “Software Agents” (Bradshaw, 1997), James Bradshaw mentions no fewer than seven possible definitions of what an agent is in the opening chapter. A review of literature by Schleiffer (2005); Hostler, Yoon and Guimaraes (2005); Chen and Su (2003); [Jensen (2002) REMOVED] Lieberman et al. (2001); Shang, Shi and Chen (2001); Wooldridge and Jennings (1998); Negroponte (1995) and Maes (1997) reveal additional definitions, each slightly different from the next. Bradshaw (1997) states that coming up with a “once-and-for-all definition of agenthood” is very difficult, because researchers and developers have so many opinions on agents, their function, and their application (p. 5). He also asserts that “there has been an explosion in the use of the term without a corresponding consensus on what it means” (p. 4). According to Bradshaw, this may be the reason that many developers mistake generic software programs for agents – “some programs are called agents simply because they can be scheduled in advance to perform tasks on a remote machine” (p. 4). Along these same lines, as Foner (1993) observes in Bradshaw (1997, p. 6), there is “little justification for most of the commercial offerings that call themselves agents. Most are barely autonomous, unless a regularly scheduled batch-job counts”. Franklin and Graesser (1996) are quick to point out that while all agents are software programs, not all software programs are agents. Petrie (1996) in Bradshaw (1997, p. 10) goes a step further by demonstrating that most of the “current Web-based searching and filtering “agents”, though useful, are essentially one-time query answering mechanisms”. Defining Agent Technology With that in mind, a cursory overview of some of the practical definitions of agents is in order. The term “agent” most often refers to a software program that gathers information or performs some other service without the immediate presence of the user. While some researchers [FININ 1997 removed] express doubt that a consensus about what an agent is will ever be reached, many researchers in the area of agent technology agree that the definition by Shoham (1997) is accurate: “A software entity which functions continuously and autonomously in a particular environment, often inhabited by other agents and processes”. Bradshaw (1997) 2 asserts that agents are able to carry out activities without constant human intervention, while Jafari (2002) sees agents as “a set of independent software tools linked with other applications and databases running within one or several computer environments. The primary function of an intelligent agent is to help a user better use, manage and interact with a computer application” (p. 29). Wooldridge (1997) describes an agent as an encapsulated computer system, situated in a particular environment, that is capable of flexible, autonomous action in that environment in order to meet its design objectives. Autonomy in this case indicates the ability to compute something, and the preferences over how they use that capability (Birmingham, 1995). Laurel (1997) includes librarians as human models for agents, stating “agents provide expertise, skill and labor. They must of necessity be capable of understanding our needs and goals in relation to them, translating those goals into an appropriate set of actions, performing those actions, and delivering results in a form that we can use” (p. 71). In addition to librarians, Laurel goes on to list teachers, secretaries and accountants as a few of the examples of real-life agents who carry out these actions. Hostler, Yoon and Guimaraes (2005) outline several classifications of agents, a typology first presented by Nwana and Ndumu: deliberative, reactive, Internet, Interface, mobile and stationary. Deliberative agents have a pre-set outline of actions to take once an event is activated by the user or system, whereas reactive agents do not store this type of script, and must meet their goals by using a “stimulus/response type of behavior” (Nwana and Ndumu, 1998, p. 30). Internet agents are those that work to reduce information overload of the user, by using spiders and crawlers to efficiently search the Web. The interface agent helps users navigate their online environment by observing actions and improving future outcomes. Agents that have the ability to “roam the network such as the World Wide Web, interacting with foreign hosts, performing the various duties assigned at a remote site, and come back to its user upon completion of the task” are known as mobile agents (Nwana and Ndumu, 1998, p. 36). An agent that does not roam is known as a stationary agent. Dent, Harris, Martinez and Hall (2001) describe how agent terminology helps users to better understand agent systems, stating, “Many of the systems where agents are at work are 3 highly complex, and understanding what tasks are being undertaken by the system can be difficult…One of the benefits of agent technology is that it provides a helpful, abstract way of talking about complicated distributed systems using basic terminology” (p.56). For example, mediator agents, communication agents and query-planning agents (Birmingham, 1995) are easily recognizable terms applied to a complex set of processes that might occur within a given environment. Sundsted (1998) describes certain characteristics of agents that are relatively exclusive: they are autonomous, have the ability to learn, mobile, persistent, goal oriented, communicative, and flexible. He further advances that although agents are small programs and limited in what they can accomplish on their own, when working in concert with other groups of agents, they can perform any number of tasks. Researchers have also tried to further specify the work done by agents. Miller’s model describes an agent architecture which includes the four functions of observation, recognition, planning and/or inference, and action or execution (1997), while Maes (1997) states that agents can help users in a number of different ways: 1. They hide the complexity of difficult tasks 2. They perform tasks on the user’s behalf 3. They can train or teach each other 4. They help different users collaborate 5. They monitor events and procedures Wooldridge and Jennings (1998) address the usefulness of agents, and state that there are two conditions that make new technology useful: the ability to solve problems that have been unsolvable with previously existing technology, and the ability to solve current problems more efficiently (p. 5). It is obvious that there are numerous ways to describe agents, from the practical to the fantastic; the challenge for those in libraries and other information service areas is to separate fact from fiction, and utilize agent technology for support and problem-solving in a way most helpful to users. A Brief Literature Review of Intelligent Agents in Practical Environments 4 A great deal of progress has been documented since the early study of the intelligent agent, and the professional literature is largely reflective of project-based exploration and research.
Load more

Recommended publications
  • Intelligent Agents
    Intelligent Agents Authors: Dr. Gerhard Weiss, SCCH GmbH, Austria Dr. Lars Braubach, University of Hamburg, Germany Dr. Paolo Giorgini, University of Trento, Italy Outline Abstract ..................................................................................................................2 Key Words ..............................................................................................................2 1 Foundations of Intelligent Agents.......................................................................... 3 2 The Intelligent Agents Perspective on Engineering .............................................. 5 2.1 Key Attributes of Agent-Oriented Engineering .................................................. 5 2.2 Summary and Challenges................................................................................ 8 3 Architectures for Intelligent Agents ...................................................................... 9 3.1 Internal Agent Architectures .......................................................................... 10 3.2 Social Agent Architectures............................................................................. 11 3.3 Summary & Challenges ................................................................................. 12 4 Development Methodologies................................................................................ 13 4.1 Overall Characterization ................................................................................ 13 4.2 Selected AO Methodologies..........................................................................
    [Show full text]
  • Intelligent Agents - Catholijn M
    ARTIFICIAL INTELLIGENCE – Intelligent Agents - Catholijn M. Jonker and Jan Treur INTELLIGENT AGENTS Catholijn M. Jonker and Jan Treur Vrije Universiteit Amsterdam, Department of Artificial Intelligence, Amsterdam, The Netherlands Keywords: Intelligent agent, Website, Electronic Commerce Contents 1. Introduction 2. Agent Notions 2.1 Weak Notion of Agent 2.2 Other Notions of Agent 3. Primitive Agent Concepts 3.1 External primitive concepts 3.2 Internal primitive concepts 3.3. An Example Analysis 4. Business Websites 5. A Generic Multi-Agent Architecture for Intelligent Websites 6. Requirements for the Website Agents 6.1 Characteristics and Requirements for the Website Agents 6.2 Characteristics and Requirements for the Personal Assistants 7. The Internal Design of the Information Broker Agents 7.1 A Generic Information Broker Agent Architecture 7.2 The Website Agent: Internal Design 7.3 The Personal Assistant: Internal Design Glossary Bibliography Biographical Sketches Summary In this article first an introduction to the basic concepts of intelligent agents is presented. The notion of weak agent is briefly described, and a number of external and internal primitive agent concepts are introduced. Next, as an illustration, application of intelligent agents to business Websites is addressed. An agent-based architecture for intelligentUNESCO Websites is introduced. Requirements – EOLSS of the agents that play a role in this architecture are discussed. Moreover, their internal design is discussed. 1. IntroductionSAMPLE CHAPTERS The term agent has become popular, and has been used for a wide variety of applications, ranging from simple batch jobs and simple email filters, to mobile applications, to intelligent assistants, and to large, open, complex, mission critical systems (such as systems for air traffic control).
    [Show full text]
  • Multi-Agent Reinforcement Learning: an Overview∗
    Delft University of Technology Delft Center for Systems and Control Technical report 10-003 Multi-agent reinforcement learning: An overview∗ L. Bus¸oniu, R. Babuska,ˇ and B. De Schutter If you want to cite this report, please use the following reference instead: L. Bus¸oniu, R. Babuska,ˇ and B. De Schutter, “Multi-agent reinforcement learning: An overview,” Chapter 7 in Innovations in Multi-Agent Systems and Applications – 1 (D. Srinivasan and L.C. Jain, eds.), vol. 310 of Studies in Computational Intelligence, Berlin, Germany: Springer, pp. 183–221, 2010. Delft Center for Systems and Control Delft University of Technology Mekelweg 2, 2628 CD Delft The Netherlands phone: +31-15-278.24.73 (secretary) URL: https://www.dcsc.tudelft.nl ∗This report can also be downloaded via https://pub.deschutter.info/abs/10_003.html Multi-Agent Reinforcement Learning: An Overview Lucian Bus¸oniu1, Robert Babuskaˇ 2, and Bart De Schutter3 Abstract Multi-agent systems can be used to address problems in a variety of do- mains, including robotics, distributed control, telecommunications, and economics. The complexity of many tasks arising in these domains makes them difficult to solve with preprogrammed agent behaviors. The agents must instead discover a solution on their own, using learning. A significant part of the research on multi-agent learn- ing concerns reinforcement learning techniques. This chapter reviews a representa- tive selection of Multi-Agent Reinforcement Learning (MARL) algorithms for fully cooperative, fully competitive, and more general (neither cooperative nor competi- tive) tasks. The benefits and challenges of MARL are described. A central challenge in the field is the formal statement of a multi-agent learning goal; this chapter re- views the learning goals proposed in the literature.
    [Show full text]
  • An Exploration in Stigmergy-Based Navigation Algorithms
    From Ants to Service Robots: an Exploration in Stigmergy-Based Navigation Algorithms عمر بهر تيری محبت ميری خدمت گر رہی ميں تری خدمت کےقابل جب هوا توچل بسی )اقبال( To my late parents with love and eternal appreciation, whom I lost during my PhD studies Örebro Studies in Technology 79 ALI ABDUL KHALIQ From Ants to Service Robots: an Exploration in Stigmergy-Based Navigation Algorithms © Ali Abdul Khaliq, 2018 Title: From Ants to Service Robots: an Exploration in Stigmergy-Based Navigation Algorithms Publisher: Örebro University 2018 www.publications.oru.se Print: Örebro University, Repro 05/2018 ISSN 1650-8580 ISBN 978-91-7529-253-3 Abstract Ali Abdul Khaliq (2018): From Ants to Service Robots: an Exploration in Stigmergy-Based Navigation Algorithms. Örebro Studies in Technology 79. Navigation is a core functionality of mobile robots. To navigate autonomously, a mobile robot typically relies on internal maps, self-localization, and path plan- ning. Reliable navigation usually comes at the cost of expensive sensors and often requires significant computational overhead. Many insects in nature perform robust, close-to-optimal goal directed naviga- tion without having the luxury of sophisticated sensors, powerful computational resources, or even an internally stored map. They do so by exploiting a simple but powerful principle called stigmergy: they use their environment as an external memory to store, read and share information. In this thesis, we explore the use of stigmergy as an alternative route to realize autonomous navigation in practical robotic systems. In our approach, we realize a stigmergic medium using RFID (Radio Frequency Identification) technology by embedding a grid of read-write RFID tags in the floor.
    [Show full text]
  • Expert Assessment of Stigmergy: a Report for the Department of National Defence
    Expert Assessment of Stigmergy: A Report for the Department of National Defence Contract No. W7714-040899/003/SV File No. 011 sv.W7714-040899 Client Reference No.: W7714-4-0899 Requisition No. W7714-040899 Contact Info. Tony White Associate Professor School of Computer Science Room 5302 Herzberg Building Carleton University 1125 Colonel By Drive Ottawa, Ontario K1S 5B6 (Office) 613-520-2600 x2208 (Cell) 613-612-2708 [email protected] http://www.scs.carleton.ca/~arpwhite Expert Assessment of Stigmergy Abstract This report describes the current state of research in the area known as Swarm Intelligence. Swarm Intelligence relies upon stigmergic principles in order to solve complex problems using only simple agents. Swarm Intelligence has been receiving increasing attention over the last 10 years as a result of the acknowledgement of the success of social insect systems in solving complex problems without the need for central control or global information. In swarm- based problem solving, a solution emerges as a result of the collective action of the members of the swarm, often using principles of communication known as stigmergy. The individual behaviours of swarm members do not indicate the nature of the emergent collective behaviour and the solution process is generally very robust to the loss of individual swarm members. This report describes the general principles for swarm-based problem solving, the way in which stigmergy is employed, and presents a number of high level algorithms that have proven utility in solving hard optimization and control problems. Useful tools for the modelling and investigation of swarm-based systems are then briefly described.
    [Show full text]
  • Intelligent Agent
    INTELLIGENT AGENT INTELLIGENT AGENT By, P.V. Raja Shekar & CH. Madhuri MRITS MCA FINAL YEAR. INTRODUCTION 1 | P a g e INTELLIGENT AGENT 1 What is artificial intelligence? 2 Branches of artificial intelligence. 3 Introduction to intelligence agent. 4 What is an agent. 5 What is a rational agent. 6 Common attributes of intelligent agent 7 What is bounded rationality. 8 What is an environment and different types of them. 9 Different agent architectures. 10 Applications . 11 Limitations . 12 Conclusion . Artificial Intelligence(AI) Artificial intelligence (AI) is both the intelligence of machines and the branch of computer science which aims to create it. Artificial Intelligence is a combination of cognitive science, linguistics, ontology, physiology, psychology, philosophy, operations research, economics, control theory, neuroscience, computer science, probability, optimization and logic. AI is a very 2 | P a g e INTELLIGENT AGENT large subject-matter. It consists of many different fields, from machine vision to expert systems. The aim of all the fields is the creation of machines that can "think". Researches hope that AI machines will be capable of reasoning, knowledge, learning, communication, planning, perception and the ability to move and manipulate objects. What's it all about? Artificial Intelligence (AI) is the science and engineering of creating intelligent machines and computer programs. It is related to similar tasks of using computers to understand human intelligence but AI does not only have to confine itself to methods that are biologically observable. The interest in AI has commonly increased since years and some classical sub- disciplines like robotics, language processing, or natural computing have produced reliable solutions Intelligence is prediction Intelligence is the ability to predict what comes next, even when faced with incomplete knowledge.
    [Show full text]
  • A Systematic Approach to Artificial Agents
    A Systematic Approach to Artificial Agents Mark Burgin1 and Gordana Dodig-Crnkovic2 1 Department of Mathematics, University of California, Los Angeles, California, USA, 2 School of Innovation, Design and Engineering, Mälardalen University, Sweden, Abstract. Agents and agent systems are becoming more and more important in the development of a variety of fields such as ubiquitous computing, ambient intelligence, autonomous computing, intelligent systems and intelligent robotics. The need for improvement of our basic knowledge on agents is very essential. We take a systematic approach and present extended classification of artificial agents which can be useful for understanding of what artificial agents are and what they can be in the future. The aim of this classification is to give us insights in what kind of agents can be created and what type of problems demand a specific kind of agents for their solution. Keywords: Artificial agents, classification, perception, reasoning, evaluation, mobility 1 Introduction Agents are advanced tools people use to achieve different goals and to various problems. The main difference between ordinary tools and agents is that agents can function more or less independently from those who delegated agency to the agents. For a long time people used only other people and sometimes animals as their agents. Developments in information processing technology, computers and their networks, have made possible to build and use artificial agents. Now the most popular approach in artificial intelligence is based on agents. Intelligent agents form a basis for many kinds of advanced software systems that incorporate varying methodologies, diverse sources of domain knowledge, and a variety of data types.
    [Show full text]
  • Adversarial Attack and Defense in Reinforcement Learning-From AI Security View Tong Chen , Jiqiang Liu, Yingxiao Xiang, Wenjia Niu*, Endong Tong and Zhen Han
    Chen et al. Cybersecurity (2019) 2:11 Cybersecurity https://doi.org/10.1186/s42400-019-0027-x SURVEY Open Access Adversarial attack and defense in reinforcement learning-from AI security view Tong Chen , Jiqiang Liu, Yingxiao Xiang, Wenjia Niu*, Endong Tong and Zhen Han Abstract Reinforcement learning is a core technology for modern artificial intelligence, and it has become a workhorse for AI applications ranging from Atrai Game to Connected and Automated Vehicle System (CAV). Therefore, a reliable RL system is the foundation for the security critical applications in AI, which has attracted a concern that is more critical than ever. However, recent studies discover that the interesting attack mode adversarial attack also be effective when targeting neural network policies in the context of reinforcement learning, which has inspired innovative researches in this direction. Hence, in this paper, we give the very first attempt to conduct a comprehensive survey on adversarial attacks in reinforcement learning under AI security. Moreover, we give briefly introduction on the most representative defense technologies against existing adversarial attacks. Keywords: Reinforcement learning, Artificial intelligence, Security, Adversarial attack, Adversarial example, Defense Introduction best moves with reinforcement learning from games of Artificial intelligence (AI) is providing major break- self-play. Meanwhile, for Atari game, Mnih et al. (2013) throughs in solving the problems that have withstood presented the first deep learning model to learn con- many attempts of natural language understanding, speech trol policies directly from high-dimensional sensory input recognition, image understanding and so on. The latest using reinforcement learning. Moreover, Liang et al. (Guo studies (He et al.
    [Show full text]
  • Extending Universal Intelligence Models with Formal Notion of Representation
    Extending Universal Intelligence Models with Formal Notion of Representation Alexey Potapov, Sergey Rodionov AIDEUS, Russia {potapov,rodionov}@aideus.com Abstract. Solomonoff induction is known to be universal, but incomputable. Its approximations, namely, the Minimum Description (or Message) Length (MDL) principles, are adopted in practice in the efficient, but non-universal form. Recent attempts to bridge this gap leaded to development of the Repre- sentational MDL principle that originates from formal decomposition of the task of induction. In this paper, possible extension of the RMDL principle in the context of universal intelligence agents is considered, for which introduction of representations is shown to be an unavoidable meta-heuristic and a step toward efficient general intelligence. Hierarchical representations and model optimiza- tion with the use of information-theoretic interpretation of the adaptive reso- nance are also discussed. Key words: Universal Agents, Kolmogorov Complexity, Minimum Descrip- tion Length Principle, Representations 1 Introduction The idea of universal induction and prediction on the basis of algorithmic information theory was invented a long time ago [1]. In theory, it eliminates the fundamental problem of prior probabilities, incorrect solutions of which result in such negative practical effects as overlearning, overfitting, oversegmentation, and so on. It would be rather natural to try to develop some models of universal intelligence on this basis. However, the corresponding detailed models were published only relatively recently (e.g. [2]). Moreover, the theory of universal induction was not popular even in ma- chine learning. The reason is quite obvious – it offers incomputable methods, which additionally require training sets of large sizes in order to make good predictions.
    [Show full text]
  • Arxiv:1607.08289V4 [Cs.AI] 21 Jan 2019 Keywords: USA CA [email protected] Francisco, San FPC, Vicarious Hay J
    1 Mammalian Value Systems Gopal P. Sarma School of Medicine, Emory University, Atlanta, GA USA [email protected] Nick J. Hay Vicarious FPC, San Francisco, CA USA [email protected] Keywords: Friendly AI, value alignment, human values, biologically inspired AI, human-mimetic AI Characterizing human values is a topic deeply interwoven with the sciences, humanities, political philosophy, art, and many other human endeavors. In recent years, a number of thinkers have argued that accelerating trends in computer science, cognitive science, and related disciplines foreshadow the creation of intelligent machines which meet and ultimately surpass the cognitive abilities of human beings, thereby entangling an understanding of human values with future technological development. Contemporary research accomplishments suggest increasingly sophisticated AI systems becoming widespread and responsible for managing many aspects of the modern world, from preemptively planning users’ travel schedules and logistics, to fully autonomous vehicles, to domestic robots assisting in daily living. The extrapolation of these trends has been most forcefully described in the context of a hypothetical “intelligence explosion,” in which the capabilities of an intelligent software agent would rapidly increase due to the presence of feedback loops unavailable to biological organisms. The possibility of super- intelligent agents, or simply the widespread deployment of sophisticated, autonomous AI systems, highlights an important theoretical problem: the need to separate
    [Show full text]
  • Intelligent Agents Web-Mining Agents
    Intelligent Agents Web-Mining Agents Prof. Dr. Ralf Möller Dr. Tanya Braun Universität zu Lübeck Institut für Informationssysteme Acknowledgements • Some slides have been designed by PD Dr. Özgür Özcep. Since Özgür works in my group, those slides are not explicitly marked. Thank you nevertheless, Özgür. • Other slides have been take from lecture material provided by researchers on the web. I hope this material is indicated appropriately. Thank you all. 2 Artificial Intelligence and Intelligent Agents • Artificial intelligence (AI) is the science of systematic synthesis and analysis of computational agents that act intelligently – Agents are central to AI (and vice versa) – Intelligent agent = computational agent that acts intelligently – Talking about AI w/o talking about agents misses the point (and vice versa) • Need to technically define the notion of “acting intelligently” • AI = Science of Intelligent Systems – Systems are called computational agents in AI, or agents for short 3 Literature http://aima.cs.berkeley.edu (AIMA, 1st edition 1995) http://artint.info st (AIFCA, 1 edition 2010) 4 Literature 5 Literature 6 What is an Agent? • Anything that can be viewed as perceiving its environment through sensors and acting upon that environment through actuators [AIMA-Def] Sensors Percepts ? Environment Agent Actions – Human agent Actuators eyes, ears, and other organs for sensors; hands, legs, mouth, and other body parts for actuators – Robotic agent cameras and infrared range finders for sensors; various motors for actuators – Software agent interfaces, data integration, interpretation, data manipulation/output 7 Abstractions: Agents and Environments Sensors Percepts ? Environment Agent Actions Actuators • The agent function maps from percept histories to actions: [f: P* à A] • The agent program runs on Really insist on functional a physical architecture to produce f behavior? • Agent = architecture + program 8 Reactive vs.
    [Show full text]
  • Using Stories to Teach Human Values to Artificial Agents
    The Workshops of the Thirtieth AAAI Conference on Artificial Intelligence AI, Ethics, and Society: Technical Report WS-16-02 Using Stories to Teach Human Values to Artificial Agents Mark O. Riedl and Brent Harrison School of Interactive Computing, Georgia Institute of Technology Atlanta, Georgia, USA friedl, [email protected] Abstract achieve a goal without doing anything “bad.” Value align- ment is a property of an intelligent agent indicating that it Value alignment is a property of an intelligent agent in- can only pursue goals that are beneficial to humans (Soares dicating that it can only pursue goals that are beneficial to humans. Successful value alignment should ensure and Fallenstein 2014; Russell, Dewey, and Tegmark 2015). that an artificial general intelligence cannot intention- Value alignment concerns itself with the definition of “good” ally or unintentionally perform behaviors that adversely and “bad,” which can subjectively differ from human to hu- affect humans. This is problematic in practice since it man and from culture to culture. is difficult to exhaustively enumerated by human pro- Value alignment is not trivial to achieve. As argued by grammers. In order for successful value alignment, we Soares (2015) and effectively demonstrated by Asimov’s argue that values should be learned. In this paper, we Robot series of books, it is very hard to directly specify val- hypothesize that an artificial intelligence that can read ues. This is because there are infinitely many undesirable and understand stories can learn the values tacitly held by the culture from which the stories originate. We de- outcomes in an open world.
    [Show full text]