Sciweavers

1912 search results - page 197 / 383
» GOAL as a Planning Formalism
Sort
View
ICML
1994
IEEE
15 years 10 months ago
Markov Games as a Framework for Multi-Agent Reinforcement Learning
In the Markov decision process (MDP) formalization of reinforcement learning, a single adaptive agent interacts with an environment defined by a probabilistic transition function....
Michael L. Littman
IADIS
2004
15 years 8 months ago
Conceptualizing Student Learning Theory
The focus of this paper is on student learning theory. Use is made of an "analytic discovery tool" called Quantitative CyberQuest (QCQ) to help conceptualize the many go...
John Dickey, Richard Larkin
AAAI
1990
15 years 7 months ago
On Acting Together
Joint action by a team does not consist merely of simultaneous and coordinated individual actions; to act together, a team must be aware of and care about the status of the group ...
Hector J. Levesque, Philip R. Cohen, José H...
AAMAS
2007
Springer
15 years 6 months ago
Conversational semantics sustained by commitments
We propose an operational model that combines message meaning and conversational structure in one comprehensive approach. Our long-term research goal is to lay down principles unit...
Roberto A. Flores, Philippe Pasquier, Brahim Chaib...
CN
2010
103views more  CN 2010»
15 years 6 months ago
Resilient and survivable networks
This poster discusses methods to characterize the resilience of networks to a number of challenges and attacks, with the goal of developing quantifiable metrics to determine the de...
Bernhard Plattner, David Hutchison, James P. G. St...