Sugawara, T. and V. R. Lesser: 1998, `Learning to Improve Coordinated Actions in Cooperative Distributed Problem-Solving Environments'. Machine Learning 33(2/3), 129153.  Home/Search   Document Details and Download   Summary   Related Articles   Check

....to design learning algorithms for cooperative multiagent tasks [84] where the agents learn the coordination skills by trial and error. The key idea here is that coordination skills are learned more e#ciently if agents learn to synchronize using a hierarchical representation of the task structure [69]. In particular, rather than each robot learning its response to low level primitive actions of the other robots (for instance, if A1 goes forward, what should A2 do) they learn high level coordination knowledge (what is the utility of A2 picking up trash from T1 if A1 is also picking up from the ....

T. Sugawara and V. Lesser. Learning to improve coordinated actions in cooperative distributed problemsolving environments. Machine Learning, 33:129--154, 1998.

....to design learning algorithms for cooperative multiagent tasks [42] where the agents learn the coordination skills by trial and error. The key idea here is that coordination skills are learned more eciently if agents learn to synchronize using a hierarchical representation of the task structure [32]. In particular, rather than each robot learning its response to low level primitive actions of the other robots (for instance, if A1 goes forward, what should A2 do) they learn high level coordination knowledge (what is the utility of A2 picking up trash from T1 if A1 is also picking up from the ....

T. Sugawara and V. Lesser. Learning to improve coordinated actions in cooperative distributed problem-solving environments. Machine Learning, 33:129-154, 1998.

....in learning algorithms for such cooperative multiagent tasks, where the agents learn the coordination skills by trial and error. The main point of the paper is simply that coordination skills are learned much more eciently if the robots have a hierarchical representation of the task structure [13]. In particular, rather than each robot learning its response to low level primitive actions of the other robots (for instance if robot 1 goes forward, what should robot 2 do) it learns high level coordination knowledge (what is the utility of robot 2 searching room 2 if robot 1 is searching ....

T. Sugawara and V. Lesser. Learning to improve coordinated actions in cooperative distributed problem-solving environments. Machine Learning, 33:129-154, 1998.

.... systems, machine learning, and conflict simulations: ffl Multi Agent Systems: As mentioned earlier, most implementations of multi agent learning continue to use reinforcement learning and neural networks techniques [1, 30, 31, 40, 41] An exception is the research developed by Sugawara and Lesser [37]. They study learning methods to acquire coordination plans in distributed problem solving environments. Specifically, they develop a distributed learning component based on EBL techniques and comparative analysis. However, they do not separate out coordination in teamwork from coordination in ....

T. Sugawara and V. Lesser. Learning to Improve Coordinated Actions in Cooperative Distributed Problem-Solving Environments. Machine Learning, 33:129--153, 1998.

....(5) Artificial Intelligence for games. 5 Related Work ffl Multi Agent Systems: As mentioned earlier, most implementations of multiagent learning continue to use reinforcement learning and neural networks techniques [36, 37, 44, 45] An exception is the research developed by Sugawara and Lesser [40]. They study learning methods to acquire coordination plans in distributed problem solving environments. Specifically, they develop a distributed learning component based on EBL techniques and comparative analysis. However, they do not separate out coordination in teamwork from coordination in ....

T. Sugawara and V. Lesser. Learning to Improve Coordinated Actions in Cooperative Distributed Problem-Solving Environments. Machine Learning, 33:129--153, 1998.

....recent work by Tara A. Estlin on how to apply multi strategy learning to improve planning efficiency and quality [Estlin, 1998] Multi Agent Learning: Most implementations of multi agent learning continue to use reinforcement learning and neural networks techniques (see [Weiss, 1999] Only [Sugawara Lesser, 1998] have used EBL techniques in a multi agent scenario. However, they do not separate out coordination in teamwork and coordination in general. As a result, they fail to exploit the responsibilities and commitments of teamwork in building up coordination relationships. Conflict Simulations: There ....

Sugawara, T. & Lesser, V. (1998). Learning to improve coordinated actions in cooperative distributed problem solving environments. Machine Learning 33: 129-153.

....by which modeling can be limited, the focus of our work is on the question of how much modeling is required for guaranteed performance the monitoring selectivity problem. We provide analytical guarantees on trade o s involved in using limited knowledge of agents for failure detection purposes. Sugawara and Lesser (1998) report on the use of comparative reasoning analysis techniques in service of learning and specializing coordination rules for a system in which distributed agents coordinate in diagnosing a faulty network. The investigation is focused on 137 ####### ### ##### optimizing coordination rules to ....

Sugawara, T., & Lesser, V. R. (1998). Learning to improve coordinated actions in cooperative distributed problem-solving environments. Machine Learning, 33 (2/3), 129153.

....coordination through joint planning (e.g. 2, 3, 6, 8, 10, 11, 17, 20] However, there are only very little approaches that combine joint learning and joint planning. There are two exceptions that are related to the JPJL algorithm. The first is the work by Sugawara and Lesser described in e.g. [21, 22]. The basic idea behind this approach is to enable agents to learn situation specific rules that capture relevant non local information in order to improve local planning and reasoning. This idea has been investigated within the context of LODES, a distributed diagnosis system for computer ....

T. Sugawara and V. Lesser, `Learning to improve coordinated actions in cooperative distributed problem-solving environments', Machine Learning, 33(2/3), 129--153, (1998).

....by which modeling can be limited, the focus of our work is on the question of how much modeling is required for guaranteed performance the monitoring selectivity problem. We provide analytical guarantees on trade o s involved in using limited knowledge of agents for failure detection purposes. Sugawara and Lesser (1998) report on the use of comparative reasoning analysis techniques in service of learning and specializing coordination rules for a system in which distributed agents coordinate in diagnosing a faulty network. The investigation is focused on 137 Kaminka and Tambe optimizing coordination rules to ....

Sugawara, T., & Lesser, V. R. (1998). Learning to improve coordinated actions in cooperative distributed problem-solving environments. Machine Learning, 33 (2/3), 129153.

.... M Dyna Q approach unique and different from a number of related approaches to multiagent activity coordination, including approaches that rely on either pure planning or pure reaction (see the references provided in Section 1) approaches that rely on a combination of planning and learning (e.g. [31, 32, 40]) and approaches that rely on a combination of reacting and learning (e.g. 2, 18, 21, 23, 28, 26, 38, 39] Obviously M Dyna Q can be considered as a generalization of these approaches, and as such it o ers maximum coordination exibility. This is not to say that M Dyna Q is always the best ....

T. Sugawara and V. Lesser. Learning to improve coordinated actions in cooperative distributed problem-solving environments. Machine Learning, 33(2/3):129-153, 1998.

.... systems, machine learning, and conflict simulations: ffl Multi Agent Systems: As mentioned earlier, most implementations of multi agent learning continue to use reinforcement learning and neural networks techniques [1, 32, 33, 42, 43] An exception is the research developed by Sugawara and Lesser [39]. They study learning methods to acquire coordination plans in distributed problem solving environments. Specifically, they develop a distributed learning component based on EBL techniques and comparative analysis. However, they do not separate out coordination in teamwork from coordination in ....

T. Sugawara and V. Lesser. Learning to Improve Coordinated Actions in Cooperative Distributed Problem-Solving Environments. Machine Learning, 33:129--153, 1998.

....(e.g. DL92, DKK97, DL91, Geo83, HD96, Kab95, SH96, Sug95, von92] However, there are only very little approaches that combine joint learning and joint planning. There are two exceptions that are related to the JPJL algorithm. The rst is the work by Sugawara and Lesser described in e.g. SL93, SL98] The basic idea behind this approach is to enable agents to learn situation speci c rules that capture relevant non local information in order to improve local planning and reasoning. This idea has been investigated within the context of LODES, a distributed diagnosis system for computer ....

T. Sugawara and V. Lesser. Learning to improve coordinated actions in cooperative distributed problem-solving environments. Machine Learning, 33(2/3):129-153, 1998.

.... problem solvers, be they process program environments, sophisticated problem solvers, or planners, are coupled with a domain independent task modeling language, T MS [5] and modules for agent coordination (GPGP GPGP2) agent scheduling (Design to Criteria) and possibly components for learning [16] and diagnosis [8] The problem solvers translate their internal representations into T MS, possibly at some level of abstraction, and these structures are passed to the control components. The full prototypical agent architecture is shown in [13] though in this paper we will concentrate on the ....

Toshi Sugawara and Victor R. Lesser. Learning to improve coordinated actions in cooperative distributed problemsolving environments. Machine Learning, 1998.

No context found.

Sugawara, T., and Lesser, V. R. 1998. Learning to improve coordinated actions in cooperative distributed problem-solving environments. Machine Learning. To appear.

.... problem solvers, be they process program environments, sophisticated problem solvers, or planners, are coupled with a domain independent task modeling language, TAEMS [10] and modules for agent coordination (GPGP GPGP2) agent scheduling (Design to Criteria) and possibly components for learning [31, 19] and diagnosis [16, 21] The problem solvers translate their internal representations into TAEMS and these structures are passed to the control components. The larger prototypical agent architecture is shown in Figure 1 and the control components that we focus on in this paper are shown in Figure ....

Toshi Sugawara and Victor R. Lesser. Learning to improve coordinated actions in cooperative distributed problem-solving environments. Machine Learning, 1998. To appear.

No context found.

Sugawara, T. and V. R. Lesser: 1998, `Learning to Improve Coordinated Actions in Cooperative Distributed Problem-Solving Environments'. Machine Learning 33(2/3), 129153.

No context found.

T. Sugawara and V. Lesser. Learning to improve coordinated actions in cooperative distributed problem-solving environments. Machine Learning, 33(2/3):129--153, 1998.

No context found.

T. Sugawara and V. Lesser, `Learning to improve coordinated actions in cooperative distributed problem-solving environments', Machine Learning, 33(2/3), 129--153, (1998).

No context found.

T. Sugawara and V. Lesser. Learning to improve coordinated actions in cooperative distributed problemsolving environments. Machine Learning, 33:129--154, 1998.

No context found.

Sugawara, T. and V. Lesser: 1998, `Learning to Improve Coordinated Actions in Cooperative Distributed Problem-Solving Environments'. Machine Learning 33(2-3), 129--153.

No context found.

T. Sugawara and V. Lesser. Learning to improve coordinated actions in cooperative distributed problem-solving environments. Machine Learning, 33:129--154, 1998.

No context found.

T. Sugawara and V. Lesser. Learning to improve coordinated actions in cooperative distributed problemsolving environments. Machine Learning, 33(2/3):129-- 153, 1998.

No context found.

T. Sugawara and V. R. Lesser. Learning to improve coordinated actions in cooperative distributed problem-solving environments. Machine Learning, 33(2/3):129--153, 1998.

No context found.

Sugawara, T. and V. R. Lesser: 1998, `Learning to Improve Coordinated Actions in Cooperative Distributed Problem-Solving Environments'. Machine Learning 33(2/3), 129153.

No context found.

Toshiharu Sugawara and Victor Lesser. Learning to improve coordinated actions in cooperative distributed problemsolving environments. Machine Learning, 33(2-3):129-- 153, 1998.

First 50 documents

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