Declaration
Download 0.56 Mb.
|
- Navigate this page:
- Advisory Agents
- Military Agents
Multi-agent systemsAgent development is shifting from a centralised agent system to collaborative multi-agent systems. A network of collaborating solver agents is one in which each agent deals with a one sub-problem. Mediator agents “match” the solutions of the solver agents. For instance, the Globus project, of Argonne National Laboratory and the University of Southern California’s Information Science Institute, provides basic software infrastructure for computations that integrate geographically disparate resources.97 The Infospheres project at Caltech provides a distributed programming layer using the Web, Java and the Internet for the purposes of delivering education materials that are customisable for specific classes. They have three goals: Intensity (higher levels of engagement); Simulation (immediate ability to practice with consequences); and Collaboration (multi-learner and real-time access to expertise knowledge).98 Software agents, both independently and through their interaction with multi-agent systems, are transforming the Internet’s already multifaceted character. Functioning through the medium of autonomous actions, agents and agent systems move onto the Net’s distributed, large-scale, dynamic structure on behalf of often-anonymous servers and human users scattered around the globe. Their purpose is to create open, flexible systems that shape future communities, commerce, and knowledge exchange. Agents linked to the electric power grid create networked “smart homes”99 and shift virtual communities by creating surrogates and aliases for people and change business and manufacturing processes. Advisory AgentsThe past few decades have seen a huge amount of sophisticated code being developed to solve specific, homogenous problems. A person cannot realistically know all possible solutions to a problem, and expecting a single agent to perform this task is equally unrealistic. To circumvent this resource selection bottleneck, developers have started working on “recommender” agents. The purpose of a recommender agent is to accept a query from a solver (or mediator) agent about a problem, determine a suitable algorithm that applies to that problem, and finally, direct it to the appropriate location on the net where software implementing the algorithm can be obtained and executed. Such agents are used extensively in commercial search engines and web-based data warehouses. The organisation of software on the Net and tracking software availability is facilitated by cross-indices of mathematical software such as GAMS.100 Each recommender agent can provide recommendations for certain class of problems and can also collaborate with other agents to collectively arrive at a recommendation. The PYTHIA agent system101 provides the recommender agents needed for multidisciplinary simulation. The interface between PYTHIA and the GAMS repository forms the basis of collaborative software. The PYTHIA agents are based on extensive performance evaluation of GAMS-indexed software (Drashansky et al 51). While PYTHIA supplies the recommender agents that interface with GAMS, the solver and mediator agents are provided by SciAgents systems. Each solver agent is considered a “black box” by the other agents and interacts with them using interagent language. SciAgents is a mechanism for cooperation among computing agents, thus moving away from the centralised, single agent systems. The agents perform only local computations and communicate only with neighbouring agents. They cooperate in solving global, complex problems without any of them exercising centralised control over the computations. The global solution emerges in well-defined mathematical way from the local computations as a result of intelligent decision-making done locally and independently by the mediator agents (Drashansky et al 52).
The framework used most for military experiments with agents is the SIM_AGENT toolkit. 102 It allows multiple agents to be run and controls their communication with each other and with the physical simulation of the battlefield. Simulated battlefield commanders or simulated antiterrorist strategists may have to detect and handle conflicts between protecting civilians and capturing opponents. These agents have already been deployed to control tanks in ground battle simulations used in military training. The terrain over which the tanks are moving and the beliefs of the enemy govern the tactical behaviour. The hierarchical structure of the SIM_AGENT system remarkably resembles that of the military. High-level commanders are given objectives that are used to produce lower-level objectives for their subordinates. Information flows both up and down the command chain and agents need to cooperate with their peers to achieve the overall goal set by their commander. This natural decomposition of the problem allows higher-level agents to work on long-term plans while the individual tank agents carry out orders designed to achieve more immediate objectives. (Baxter and Hepplewhite 74) e-commerce Agents According to Forrester Research, agents and the business performance they deliver will be involved in up to $327 billion worth of Net-based commerce in five years (Maes 79). Not surprisingly, an agent development industry has sprung to supply agents and associated technology to online brokerages, auction houses, catalogues, and others. The agents automatically buy and sell merchandise, negotiate contracts, and interact with remote human customers. Amazon.com may be the best current example of a successful use of agent technology for e-commerce. The company uses the Firefly agent developed by the Software Agent group at MIT, under the leadership of Pattie Maes. She is one of the leading figures in developing agents for e-commerce. Maes, along with Robert Guttman and Alexandre Moukas from an MIT spin-off company, Frictionless Commerce Inc., identify the following as fundamental stages of the buying process: Need identification; Product brokering; Merchant brokering; Negotiation; Purchase and delivery; and product service evaluation. Agents thus become the mediators in e-commerce103 (Maes 83). As agent technology matures and agent applications become more common, developers will want to integrate multiple applications so that different systems collaborate synergistically. Agents will be able to use their knowledge to dynamically negotiate software interfaces, enabling them to self-organise, forming super-applications at run-time. Super-applications will embody a new generation of scaleable, cost-effective technology.
Directory: publications publications -> Acm word Template for sig site publications -> Preparation of Papers for ieee transactions on medical imaging publications -> Adjih, C., Georgiadis, L., Jacquet, P., & Szpankowski, W. (2006). Multicast tree structure and the power law publications -> Swiss Federal Institute of Technology (eth) Zurich Computer Engineering and Networks Laboratory publications -> Quantitative skills publications -> Multi-core cpu and gpu implementation of Discrete Periodic Radon Transform and Its Inverse publications -> List of Publications Department of Mechanical Engineering ucek, jntu kakinada publications -> 1. 2 Authority 1 3 Planning Area 1 publications -> Sa michelson, 2011: Impact of Sea-Spray on the Atmospheric Surface Layer. Bound. Layer Meteor., 140 ( 3 ), 361-381, doi: 10. 1007/s10546-011-9617-1, issn: Jun-14, ids: 807TW, sep 2011 Bao, jw, cw fairall, sa michelson Download 0.56 Mb. Share with your friends:
|