69 search results - page 3 / 14 » Goal Achievement in Partially Known, Partially Observable Do... |
172
click to vote
ICML
1999
IEEE
16 years 6 months ago
1999
IEEE
We present a learning algorithm for non-parametric hidden Markov models with continuous state and observation spaces. All necessary probability densities are approximated using sa...
160
click to vote
GLOBECOM
2008
IEEE
16 years 13 days ago
2008
IEEE
Abstract—A network with two sensors communicating a remote measurement to a common access point (AP) is investigated. The sensors are connected via out-of-band and finite-capaci...
146
click to vote
ICRA
2007
IEEE
16 years 9 days ago
2007
IEEE
— While the Partially Observable Markov Decision Process (POMDP) provides a formal framework for the problem of robot control under uncertainty, it typically assumes a known and ...
182
click to vote
FOCS
2007
IEEE
16 years 9 days ago
2007
IEEE
We consider a variant of the classic multi-armed bandit problem (MAB), which we call FEEDBACK MAB, where the reward obtained by playing each of n independent arms varies according...
150
click to vote
AI
2006
Springer
15 years 9 months ago
2006
Springer
So far, most equilibrium concepts in game theory require that the rewards and actions of the other agents are known and/or observed by all agents. However, in real life problems, a...