The AnimaTricks System: Animating Intelligent Agents from High-Level Goal Declarations

2012 ◽  
pp. 203-208
Author(s):  
Vincenzo Lombardo ◽  
Fabrizio Nunnari ◽  
Rossana Damiano
Keyword(s):  
Intelligent Agents ◽  
High Level

Software Agents in Today's Digital Economy

2001 ◽  
pp. 88-100 ◽  
Author(s):  
Mahesh S. Raisinghani
Keyword(s):  
Intelligent Agents ◽  
New Technology ◽  
Software Agents ◽  
Information Filtering ◽  
Intelligent Agent ◽  
Social Dimension ◽  
Economic Changes ◽  
Software Products ◽  
Intelligent Software Agents ◽  
High Level

One of the most discussed topics in the information systems literature today is software agent/intelligent agent technology. Software agents are high-level software abstractions with inherent capabilities for communication, decision making, control, and autonomy. They are programs that perform functions such as information gathering, information filtering, or mediation (running in the background) on behalf of a person or entity. They have several aliases such as agents, bots, chatterbots, databots, intellibots, and intelligent software agents/robots. They provide a powerful mechanism to address complex software engineering problems such as abstraction, encapsulation, modularity, reusability, concurrency, and distributed operations. Much research has been devoted to this topic, and more and more new software products billed as having intelligent agent functionality are being introduced on the market every day. The research that is being done, however, does not wholeheartedly endorse this trend. The current research into intelligent agent software technology can be divided into two main areas: technological and social. The latter area is particularly important since, in the excitement of new and emergent technology, people often forget to examine what impact the new technology will have on people’s lives. In fact, the social dimension of all technology is the driving force and most important consideration of technology itself. This chapter presents a socio-technical perspective on intelligent agents and proposes a framework based on the data lifecycle and knowledge discovery using intelligent agents. One of the key ideas of this chapter is best stated by Peter F. Drucker in Management Challenges for the 21st Century when he suggests that in this period of profound social and economic changes, managers should focus on the meaning of information, not the technology that collects it.

Intelligent Software Agents in Electronic Commerce

2011 ◽  
pp. 104-112 ◽  
Author(s):  
Mahesh S. Raisinghani ◽  
Christopher Klassen ◽  
Lawrence L. Schkade
Keyword(s):  
Intelligent Agents ◽  
Software Agents ◽  
Intelligent Agent ◽  
Software Agent ◽  
Reasoning Strategies ◽  
Intelligent Software ◽  
Collaborative Behavior ◽  
Intelligent Software Agents ◽  
The Status ◽  
High Level

Although there is no firm consensus on what constitutes an intelligent agent (or software agent), an intelligent agent, when a new task is delegated by the user, should determine precisely what its goal is, evaluate how the goal can be reached in an effective manner, and perform the necessary actions by learning from past experience and responding to unforeseen situations with its adaptive, self-starting, and temporal continuous reasoning strategies. It needs to be not only cooperative and mobile in order to perform its tasks by interacting with other agents but also reactive and autonomous to sense the status quo and act independently to make progress towards its goals (Baek et al., 1999; Wang, 1999). Software agents are goal-directed and possess abilities such as autonomy, collaborative behavior, and inferential capability. Intelligent agents can take different forms, but an intelligent agent can initiate and make decisions without human intervention and have the capability to infer appropriate high-level goals from user actions and requests and take actions to achieve these goals (Huang, 1999; Nardi et al., 1998; Wang, 1999). The intelligent software agent is a computational entity than can adapt to the environment, making it capable of interacting with other agents and transporting itself across different systems in a network.

scholarly journals Applying Software Engineering to Agent Development

AI Magazine ◽  
2010 ◽  
Vol 31 (2) ◽  
pp. 25 ◽  
Author(s):  
Mark A. Cohen ◽  
Frank E. Ritter ◽  
Steven R Haynes
Keyword(s):  
Software Engineering ◽  
Software Reuse ◽  
Intelligent Agents ◽  
Intelligent Agent ◽  
Integrated Development Environment ◽  
Development Environment ◽  
Integrated Development ◽  
Engineering Activity ◽  
High Level ◽  
Agent Development

Developing intelligent agents and cognitive models is a complex software engineering activity. This article shows how all intelligent agent creation tools can be improved by taking advantage of established software engineering principles such as high-level languages, maintenance-oriented development environments, and software reuse. We describe how these principles have been realized in the Herbal integrated development environment, a collection of tools that allows agent developers to exploit modern software engineering principles.

Towards life-long adaptive agents: using metareasoning for combining knowledge-based planning with situated learning

2018 ◽  
Vol 33 ◽  
Author(s):  
Priyam Parashar ◽  
Ashok K. Goel ◽  
Bradley Sheneman ◽  
Henrik I. Christensen
Keyword(s):  
Situated Learning ◽  
Intelligent Agents ◽  
Physical World ◽  
Task Planning ◽  
Adaptive Agents ◽  
Hierarchical Task Network ◽  
Knowledge Based ◽  
Knowledge Based Planning ◽  
Occupancy Grids ◽  
High Level

AbstractWe consider task planning for long-living intelligent agents situated in dynamic environments. Specifically, we address the problem of incomplete knowledge of the world due to the addition of new objects with unknown action models. We propose a multilayered agent architecture that uses meta-reasoning to control hierarchical task planning and situated learning, monitor expectations generated by a plan against world observations, forms goals and rewards for the situated reinforcement learner, and learns the missing planning knowledge relevant to the new objects. We use occupancy grids as a low-level representation for the high-level expectations to capture changes in the physical world due to the additional objects, and provide a similarity method for detecting discrepancies between the expectations and the observations at run-time; the meta-reasoner uses these discrepancies to formulate goals and rewards for the learner, and the learned policies are added to the hierarchical task network plan library for future re-use. We describe our experiments in the Minecraft and Gazebo microworlds to demonstrate the efficacy of the architecture and the technique for learning. We test our approach against an ablated reinforcement learning (RL) version, and our results indicate this form of expectation enhances the learning curve for RL while being more generic than propositional representations.

Intelligent Agents for Competitive Advantage

2011 ◽  
pp. 25-34
Author(s):  
Mahesh Raisinghani ◽  
John H. Nugent
Keyword(s):  
Decision Making ◽  
Information Systems ◽  
Competitive Advantage ◽  
Cycle Time ◽  
Intelligent Agents ◽  
Business Management ◽  
Telecommunications Networks ◽  
Management Processes ◽  
Level Model ◽  
High Level

This chapter presents a high-level model for employing intelligent agents in business management processes, much like has been successfully accomplished in complex telecommunications networks, in order to gain competitive advantage by timely, rapidly, and effectively using key, unfiltered measurements to improve cycle-time decision making. The importance of automated, timely, unfiltered (versus “end of period” filtered) reports is highlighted, as are some management issues relative to the pressures that may result concerning an organization’s employees who must now take action in near real time. Furthermore, the authors hope that understanding the underlying assumptions and theoretical constructs through the use of employing intelligent agents in business management processes as a sub element of, or tool within Business Intelligence (BI), will not only inform researchers of a better design for studying information systems, but also assist in the understanding of intricate relationships between different factors.

Cooperative Human-Computer Decision Making: An Experiment and Some Design Implications

1994 ◽  
Vol 38 (4) ◽  
pp. 220-224 ◽  
Author(s):  
Gunilla A. Sundström ◽  
Anthony C. Salvador
Keyword(s):  
Decision Making ◽  
Fault Diagnosis ◽  
Decision Maker ◽  
Confidence Level ◽  
Intelligent Agents ◽  
Network Performance ◽  
Wrong Decision ◽  
Human Decision ◽  
Types Of Information ◽  
High Level

Creating useful dialogues between human and automated decision makers (i.e., intelligent agents) is a critical design aspect of any effective decision support environment. However, surprisingly few studies have examined the various factors influencing the way a human decision maker interacts with various types of intelligent agents. In the present work, one such factor was examined, namely the confidence expressed by the agent about its own conclusions. Subjects were trained in a network management fault diagnosis task. They were then asked to accept or reject a fault diagnosis generated by the automated decision making agent. The automated decision maker presented its fault diagnosis with an associated confidence indication expressed as a probability. Subjects were required to decide whether to accept or reject the automated decision maker's diagnosis. To conceive an informed response, subjects were able to examine various types of information related to network performance. The results indicated that the higher the confidence level presented by the automated decision maker, the more likely it was that the human decision maker would accept the automatically generated diagnosis. Thus, the higher the confidence level of the automated decision maker, the more likely subjects were to accept a wrong decision. Moreover, subjects examined fewer pieces of information in situations when the automated decision maker expressed a high level of confidence.

Toward Agent-Oriented Conceptualization and Implementation

2011 ◽  
pp. 1-25
Author(s):  
Pratik K. Biswas
Keyword(s):  
Software Engineering ◽  
Intelligent Agents ◽  
Multi Agent Systems ◽  
New Paradigm ◽  
Agent Based ◽  
Future Challenges ◽  
Multi Agent ◽  
High Level ◽  
Traditional Approaches ◽  
Systems Framework

The desire to flexibly customize software, manage it efficiently, and empower it with intelligence has driven research and development-related efforts toward intelligent agents. The benefits in terms of rapid delivery, reduced costs, and enhanced productivity can be realized in the areas of systems and software engineering with the proliferation of this technology. Intelligent agents represent an alternate approach to distributed software engineering. Agent-oriented conceptualization provides a new paradigm for the design and development of these agent-based systems. This chapter extends and formalizes this agent oriented modeling approach to the conceptualization process. It defines agent models and proposes a high-level methodology for agent-oriented analysis and design. It also looks at the heart of agent-oriented programming and outlines its advantages over traditional approaches to distributed computing and interoperability. The chapter includes analogies with the object-oriented methodologies and other existing agent-oriented methodologies wherever applicable. It reviews the Foundation of Intelligent Physical Agents-compliant infrastructure for building agent-based systems and suggests a multi-agent systems framework that merges this infrastructure with the emerging J2EE technologies. The chapter concludes with a case study and an insight to future challenges.

Impact Analysis of Intelligent Agents in Automatic Fault-Prone Components Prediction and Testing

2018 ◽  
pp. 287-316
Author(s):  
Jeya Mala Dharmalingam
Keyword(s):  
Software Quality ◽  
Intelligent Agents ◽  
Impact Analysis ◽  
Critical Value ◽  
Agent Based ◽  
Critical Components ◽  
High Level ◽  
Industrial Strength

Software quality is imperative for industrial strength software. This quality will be often determined by a few components present in the software which decides the entire functionality. If any of these components are not rigorously tested, the quality will be highly affected. Without knowing which of these components are really critical, it will not be possible to perform high level testing. Hence, to predict such fault-prone or critical components from the software prior to testing and prioritizing them during the testing process, an agent-based approach is proposed in this chapter. The framework developed as part of this work will certainly reduce the field failures and thus will improve the software quality. Further, this approach has also utilized important metrics to predict such components and also prioritized the components based on their critical value. Also, the work proposed in this research has also been compared with some of the existing approaches and the results reveal that, this work is a novel one and can both predict and test the components from the software.

Designing Agents with Negotiation Capabilities

2011 ◽  
pp. 1053-1058
Author(s):  
Jana Polgar
Keyword(s):  
User Interfaces ◽  
Intelligent Agents ◽  
Technology Use ◽  
Autonomous Agents ◽  
New Technologies ◽  
Optimization Problems ◽  
Negotiation Strategy ◽  
Negotiation Strategies ◽  
High Level ◽  
Reasoning Engine

Agents are viewed as the next significant software abstraction, and it is expected they will become as ubiquitous as graphical user interfaces are today. Agents are specialized programs designed to provide services to their users. Multiagent systems have a key capability to reallocate tasks among the members, which may result in significant savings and improvements in many domains, such as resource allocation, scheduling, e-commerce, and so forth. In the near future, agents will roam the Internet, selling and buying information and services. These agents will evolve from their present day form - simple carriers of transactions - to efficient decision makers. It is envisaged that the decisionmaking processes and interactions between agents will be very fast (Kephart, 1998). The importance of automated negotiation systems is increasing with the emergence of new technologies supporting faster reasoning engines and mobile code. A central part of agent systems is a sophisticated reasoning engine that enables the agents to reallocate their tasks, optimize outcomes, and negotiate with other agents. The negotiation strategy used by the reasoning engine also requires high-level inter-agent communication protocols, and suitable collaboration strategies. Both of these sub-systems – a reasoning engine and a negotiation strategy - typically result in complicated agent designs and implementations that are difficult to maintain. Activities of a set of autonomous agents have to be coordinated. Some could be mobile agents, while others are static intelligent agents. We usually aim at decentralized coordination, which produces the desired outcomes with minimal communication. Many different types of contract protocols (cluster, swaps, and multiagent, as examples) and negotiation strategies are used. The evaluation of outcomes is often based on marginal cost (Sandholm, 1993) or game theory payoffs (Mass-Colell, 1995). Agents based on constraint technology use complex search algorithms to solve optimization problems arising from the agents’ interaction. In particular, coordination and negotiation strategies in the presence of incomplete knowledge are good candidates for constraint-based implementations.

Sign in / Sign up

Export Citation Format

Share Document