Sciweavers

250 search results - page 41 / 50
» Learning action effects in partially observable domains
Sort
View
ARGMAS
2004
Springer
15 years 3 months ago
Is It Worth Arguing?
Argumentation-based negotiation (ABN) is an effective means of resolving conflicts in a multi-agent society. However, it consumes both time and computational resources for agents ...
Nishan C. Karunatillake, Nicholas R. Jennings
ICRA
2005
IEEE
138views Robotics» more  ICRA 2005»
15 years 3 months ago
The Role of Motion Information in Learning Human-Robot Joint Attention
— To realize natural human-robot interactions and investigate the developmental mechanism of human communication, an effective approach is to construct models by which a robot im...
Yukie Nagai
ICMLA
2008
14 years 11 months ago
Semi-supervised IFA with Prior Knowledge on the Mixing Process: An Application to a Railway Device Diagnosis
Independent Factor Analysis (IFA) is a well known method used to recover independent components from their linear observed mixtures without any knowledge on the mixing process. Su...
Etienne Côme, Zohra Leila Cherfi, Latifa Ouk...
ML
1998
ACM
101views Machine Learning» more  ML 1998»
14 years 9 months ago
Elevator Group Control Using Multiple Reinforcement Learning Agents
Recent algorithmic and theoretical advances in reinforcement learning (RL) have attracted widespread interest. RL algorithmshave appeared that approximatedynamic programming on an ...
Robert H. Crites, Andrew G. Barto
HRI
2007
ACM
15 years 1 months ago
Efficient model learning for dialog management
Intelligent planning algorithms such as the Partially Observable Markov Decision Process (POMDP) have succeeded in dialog management applications [10, 11, 12] because of their rob...
Finale Doshi, Nicholas Roy