Matches in SemOpenAlex for { <https://semopenalex.org/work/W204613853> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W204613853 abstract "The work presented here deals with ways to improve problem solving control skills of cooperative agents. We propose situation-specific learning as a way to learn cooperative control knowledge in complex multi-agent systems. We demonstrate the power of situation-specific learning in the context of dynamic choice of a coordination strategy based on the problem solving situation. We present a leaming system, called COLLAGE, that uses meta-level information in the form of abstract characterization of the coordination problem instance to leam to choose the appropriate coordination strategy from among a class of strategies. The work presented here deals with ways to improve problem solving control skills of cooperative agents. Problem solving control is the process by which an agent organizes its computation. An agent in a MAS faces control uncertainties due to its partial local view of the problem solving states of the other agents in the system. Uncertainties about progress of problem solving in other agents, characteristics of non-local interacting sub-problems, expectations of non-local problemsolving activity, and generated partial results can lead to global incoherence and degradation in system performance if they are not managed effectively through cooperation. Effective cooperation in such systems requires that the global problemsolving state influence the local control decisions made by an agent. We call such an influence cooperative control(Lesser 1991). Cooperation among agents can be explicit or implicit. In explicitly cooperative systems, the agents interact and exchange information or perform actions so as to benefit other agents. On the other hand, implicitly cooperative agents perform actions that are a part of their own goal-seeking process but these actions affect the other agents in beneficial ways(Mataric 1993). Agents exchange information through communication. An agent in a MAS needs to communicate with other agents to acquire a view of the non-local problem solving so as to make local decisions that are influenced by more global considerations. The agents perform direct communication or indirect communication as a part of their process of interaction with other agents. Direct communication involves intentionality entailing a sender and one or more receivers. The communication is purposeful and is aimed at particular members of *This material is based upon work supported by the National Science Foundation under Grant Nos. IRI-9523419. The content of this paper does not necessarily reflect the position or the policy of the Government, and no official endorsement should be inferred. the agent set. Much of the explicitly cooperative activities involves direct communication. In contrast, indirect communication is achieved through observation of the behavior of the other agents and their effects on the environment(Mataric 1993). Indirect communication involves cues that are simply by-products of behaviors performed for reasons other than communication(Seeley 1989). In this paper, we deal with an explicitly cooperative directly communicating system. In such systems, the local problem solving control of an agent can interact in complex and intricate ways with the problem solving control of other agents. In these systems, an agent cannot make effective control decisions based on purely local problem solving state. A given local problem solving state can map to a multitude of global problem solving states. An agent with a purely local view of the problem solving situation cannot learn effective control de" @default.
- W204613853 created "2016-06-24" @default.
- W204613853 creator A5020207982 @default.
- W204613853 creator A5069043950 @default.
- W204613853 date "1997-01-01" @default.
- W204613853 modified "2023-09-27" @default.
- W204613853 title "Learning Problem Solving Control in Cooperative Multi-Agent Systems*" @default.
- W204613853 cites W125070426 @default.
- W204613853 cites W1624695774 @default.
- W204613853 cites W1641379095 @default.
- W204613853 cites W1896158234 @default.
- W204613853 cites W2053173980 @default.
- W204613853 cites W2117341272 @default.
- W204613853 cites W2121903938 @default.
- W204613853 cites W2142839172 @default.
- W204613853 cites W2147169507 @default.
- W204613853 cites W2262420275 @default.
- W204613853 cites W364583 @default.
- W204613853 cites W44112122 @default.
- W204613853 hasPublicationYear "1997" @default.
- W204613853 type Work @default.
- W204613853 sameAs 204613853 @default.
- W204613853 citedByCount "2" @default.
- W204613853 crossrefType "journal-article" @default.
- W204613853 hasAuthorship W204613853A5020207982 @default.
- W204613853 hasAuthorship W204613853A5069043950 @default.
- W204613853 hasConcept C111919701 @default.
- W204613853 hasConcept C11413529 @default.
- W204613853 hasConcept C126255220 @default.
- W204613853 hasConcept C151730666 @default.
- W204613853 hasConcept C154945302 @default.
- W204613853 hasConcept C2775924081 @default.
- W204613853 hasConcept C2777212361 @default.
- W204613853 hasConcept C2779343474 @default.
- W204613853 hasConcept C33923547 @default.
- W204613853 hasConcept C41008148 @default.
- W204613853 hasConcept C41550386 @default.
- W204613853 hasConcept C48103436 @default.
- W204613853 hasConcept C86803240 @default.
- W204613853 hasConcept C98045186 @default.
- W204613853 hasConceptScore W204613853C111919701 @default.
- W204613853 hasConceptScore W204613853C11413529 @default.
- W204613853 hasConceptScore W204613853C126255220 @default.
- W204613853 hasConceptScore W204613853C151730666 @default.
- W204613853 hasConceptScore W204613853C154945302 @default.
- W204613853 hasConceptScore W204613853C2775924081 @default.
- W204613853 hasConceptScore W204613853C2777212361 @default.
- W204613853 hasConceptScore W204613853C2779343474 @default.
- W204613853 hasConceptScore W204613853C33923547 @default.
- W204613853 hasConceptScore W204613853C41008148 @default.
- W204613853 hasConceptScore W204613853C41550386 @default.
- W204613853 hasConceptScore W204613853C48103436 @default.
- W204613853 hasConceptScore W204613853C86803240 @default.
- W204613853 hasConceptScore W204613853C98045186 @default.
- W204613853 hasLocation W2046138531 @default.
- W204613853 hasOpenAccess W204613853 @default.
- W204613853 hasPrimaryLocation W2046138531 @default.
- W204613853 hasRelatedWork W1506787475 @default.
- W204613853 hasRelatedWork W1574927730 @default.
- W204613853 hasRelatedWork W1809265768 @default.
- W204613853 hasRelatedWork W191791718 @default.
- W204613853 hasRelatedWork W1977960750 @default.
- W204613853 hasRelatedWork W2048740076 @default.
- W204613853 hasRelatedWork W2091299493 @default.
- W204613853 hasRelatedWork W2116924118 @default.
- W204613853 hasRelatedWork W2244138575 @default.
- W204613853 hasRelatedWork W2462355218 @default.
- W204613853 hasRelatedWork W2471081794 @default.
- W204613853 hasRelatedWork W2498545834 @default.
- W204613853 hasRelatedWork W2885857978 @default.
- W204613853 hasRelatedWork W2898426924 @default.
- W204613853 hasRelatedWork W2946057828 @default.
- W204613853 hasRelatedWork W2979363950 @default.
- W204613853 hasRelatedWork W2980784261 @default.
- W204613853 hasRelatedWork W3209040445 @default.
- W204613853 hasRelatedWork W76925175 @default.
- W204613853 hasRelatedWork W78678285 @default.
- W204613853 isParatext "false" @default.
- W204613853 isRetracted "false" @default.
- W204613853 magId "204613853" @default.
- W204613853 workType "article" @default.