Sciweavers

1407 search results - page 173 / 282
» Sponsored Search with Contexts
Sort
View
IJCAI
2003
13 years 11 months ago
Multiple-Goal Reinforcement Learning with Modular Sarsa(0)
We present a new algorithm, GM-Sarsa(0), for finding approximate solutions to multiple-goal reinforcement learning problems that are modeled as composite Markov decision processe...
Nathan Sprague, Dana H. Ballard
RANLP
2003
13 years 11 months ago
A framework for named entity recognition in the open domain
In this paper, a system for Named Entity Recognition in the Open domain (NERO) is described. It is concerned with recognition of various types of entity, types that will be approp...
Richard J. Evans
ICMAS
1998
13 years 11 months ago
How Much Should an Agent Know what Other Agents are Doing in a Cooperative Team?
Cooperation ina task oriented multi-agent team is important because a well designed cooperation strategy among a group of cooperating agents can lead to an increase of the group p...
Yiming Ye
AAAI
1994
13 years 11 months ago
Activity Analysis: The Qualitative Analysis of Stationary Points for Optimal Reasoning
We present a theory of a modeler's problem decomposition skills in the context of optimal reasonzng -- the use of qualitative modeling to strategically guide numerical explor...
Brian C. Williams, Jonathan Cagan
COLING
1996
13 years 11 months ago
Processing Metonymy- a Domain-Model Heuristic Graph Traversal Approach
We address here the treatment of metonymic expressions from a knowledge representation perspective, that is, in the context of a text understanding system which aims to build a co...
Jacques Bouaud, Bruno Bachimont, Pierre Zweigenbau...