Sciweavers

110 search results - page 19 / 22
» Multiagent Planning as Control Synthesis
Sort
View
CIIA
2009
13 years 8 months ago
Dynamic Scheduling in Petroleum Process using Reinforcement Learning
Petroleum industry production systems are highly automatized. In this industry, all functions (e.g., planning, scheduling and maintenance) are automated and in order to remain comp...
Nassima Aissani, Bouziane Beldjilali
ML
1998
ACM
220views Machine Learning» more  ML 1998»
13 years 7 months ago
Learning to Improve Coordinated Actions in Cooperative Distributed Problem-Solving Environments
Abstract. Coordination is an essential technique in cooperative, distributed multiagent systems. However, sophisticated coordination strategies are not always cost-effective in all...
Toshiharu Sugawara, Victor R. Lesser
ATAL
2010
Springer
13 years 8 months ago
Cultivating desired behaviour: policy teaching via environment-dynamics tweaks
In this paper we study, for the first time explicitly, the implications of endowing an interested party (i.e. a teacher) with the ability to modify the underlying dynamics of the ...
Zinovi Rabinovich, Lachlan Dufton, Kate Larson, Ni...
ATAL
2009
Springer
14 years 2 months ago
From DPS to MAS to ...: continuing the trends
The most important and interesting of the computing challenges we are facing are those that involve the problems and opportunities afforded by massive decentralization and disinte...
Michael N. Huhns
IJCAI
1997
13 years 8 months ago
Reasoning about Concurrent Execution Prioritized Interrupts, and Exogenous Actions in the Situation Calculus
As an alternative to planning, an approach to highlevel agent control based on concurrent program execution is considered. A formal definition in the situation calculus of such a ...
Giuseppe De Giacomo, Yves Lespérance, Hecto...