Sciweavers

3084 search results - page 141 / 617
» Learning to Take Actions
Sort
View
AAMAS
2005
Springer
14 years 10 months ago
Learning and Exploiting Relative Weaknesses of Opponent Agents
Agents in a competitive interaction can greatly benefit from adapting to a particular adversary, rather than using the same general strategy against all opponents. One method of s...
Shaul Markovitch, Ronit Reger
HICSS
2009
IEEE
135views Biometrics» more  HICSS 2009»
15 years 4 months ago
The Role of Social Capital in the Creation of Community Wireless Networks
Community wireless networks (CWNs) offer free or affordable Internet access for the purpose of improving the well-being of the community. Many questions have been raised about the...
Abdelnasser Abdelaal, Hesham H. Ali, Deepak Khazan...
ICRA
2007
IEEE
154views Robotics» more  ICRA 2007»
15 years 4 months ago
Oracular Partially Observable Markov Decision Processes: A Very Special Case
— We introduce the Oracular Partially Observable Markov Decision Process (OPOMDP), a type of POMDP in which the world produces no observations; instead there is an “oracle,” ...
Nicholas Armstrong-Crews, Manuela M. Veloso
ICANN
2007
Springer
15 years 4 months ago
Biasing Neural Networks Towards Exploration or Exploitation Using Neuromodulation
Abstract. Taking neuromodulation as a mechanism underlying emotions, this paper investigates how such a mechanism can bias an artificial neural network towards exploration of new ...
Karla Parussel, Lola Cañamero
ATAL
2005
Springer
15 years 3 months ago
Informed Deliberation During Norm-Governed Practical Reasoning
A norm-governed agent takes social norms into account in its practical reasoning. Such norms characterise its role within a specific organisational context. By adopting a role, th...
Martin J. Kollingbaum, Timothy J. Norman