Shaw, M. and A.B. Whinston (1989) Learning and Adaptation in Distributed Artificial Intelligence Systems, in L. Gasser and M.N. Huhns (eds.) Distributed Artificial Intelligence Vol. II, Pitman Publ. Co. London, pp. 413-429.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....independently from internal representations, following an object oriented approach. One of the most commonly used and formally specified communication and negotiation framework is the contract net protocol [10] 43] which has been applied in YAMS [35] and in the system of Shaw and Whinston [42]. organisation. The representation of organisational issues is crucial in the system architecture of computational models. The modelling of authority structure, element groupings and coalitions, is essential both in the OIS and PMS fields. Examples of such organisations are hierarchical, nested ....

Shaw, M. and A.B. Whinston (1989) Learning and Adaptation in Distributed Artificial Intelligence Systems, in L. Gasser and M.N. Huhns (eds.) Distributed Artificial Intelligence Vol. II, Pitman Publ. Co. London, pp. 413-429.

....similar concepts with di#erent names, i.e. the problem of di#erent agents having di#ering vocabularies. As mentioned earlier all the systems (except ILS) described below are homogeneous that is every agent uses the same learning algorithm. The earliest reported systems are Gams, Shaws, Shaw89] INTEG.3, Brazdil91b] MALE [Sian91] and ILS [Silver90] MAMaLS [Masood92] is also homogeneous, but examines a new high level communication metaphor this will be discussed in the next chapter. Multi Agent Learning systems have been characterised as being of one of three basic forms ....

M. J. Shaw and A. B. Whinston. Learning and Adaptation in Distributed Artificial Intelligence Systems. In L. Gasser and M. Huhns, (Eds), Distributed Artificial Intelligence. Springer-Verlag, 1989, 413--427.

....costs and problems associated with communication, a growing body of research in applying learning to multiagent systems [28] 35] suggests learning as an alternative knowledge acquisition method. Among the first to explicitly address the issue of learning in DAI is the work by Shaw and Whinston [32] on an adaptive announcing and bidding mechanism for the contract net protocol. Another learning extension to the contract net framework to reduce communication is found in [11] A number of works have applied learning to the problem of coordination. This approach differs from communication based ....

Michael J. Shaw and Andrew B. Whinston. Learning and adaptation in distributed artificial intelligence systems. In L. Gasser and M. N. Huhns, editors, Distributed Artificial Intelligence, volume 2, pages 413--429, London, 1989. Pitman.

....to improve their collective behavior. Unfortunately, in contrast to this agreement, distributed learning has been neglected by the artificial intelligence community for a long time, and it is only since the last few years that there are increased research efforts. For instance, Shaw and Whinston [43] proposed a general framework for incorporating learning in multi agent systems. Brazdil and Muggleton [9] explored multi agent concept formation and knowledge integration. Sian [44] analyzed consensus learning and collective hypotheses generation. Sian [45] and Sikora and Shaw [46] did the first ....

M.J. Shaw and A.B. Whinston, Learning and adaptation in distributed artificial intelligence, in: L. Gasser and M.N. Huhns, eds., Distributed Artificial Intelligence, vol. 2 (Pitman, London, 1989) 413--429.

....costs and problems associated with communication, a growing body of research in applying learning to multi agent systems [28] 35] suggests learning as an alternative knowledge acquisition method. Among the first to explicitly address the issue of learning in DAI is the work by Shaw and Whinston [32] on an adaptive announcing and bidding mechanism for the contract net protocol. Another learning extension to the contract net framework to reduce communication is found in [11] Work by several authors has applied learning to the problem of coordination. This approach differs from ....

Michael J. Shaw and Andrew B. Whinston. Learning and adaptation in distributed artificial intelligence systems. In L. Gasser and M. N. Huhns, editors, Distributed Artificial Intelligence, volume 2, pages 413--429, London, 1989. Pitman.

.... [16] The contributions of this paper to DAI, therefore, include the rigorous development of an alternative, ecological perspective, and the idea of modifying populations rather than individuals (what I above called trading rather than training ) with implications for learning in DAI systems [82]. The paper by Mazer entitled Reasoning About Knowledge to Understand Distributed AI Systems also develops a rigorous treatment of distributed computing systems, but its purpose is to improve our understanding of two early approaches that have continued to be influential in DAI: Contract Net ....

Michael J. Shaw and Andrew B. Whinston. Learning and adaptation in distributed artificial intelligence systems. In Les Gasser and Michael N. Huhns, editors, Distributed Artificial Intelligence, volume 2 of Research Notes in Artificial Intelligence. Pitman, 1989.

No context found.

M. Shaw & A. Whinston, "Learning and Adaptation in Distributed Artificial Intelligence Systems ", in M. Huhns & L. Gasser (eds.): Distributed Artificial Intelligence, Vol.2, Morgan Kaufmann Publ., CA, 1989, pp. 413-429.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC