5771 search results - page 234 / 1155 » Learning similarity space |
190
click to vote
IJCAI
2007
15 years 8 months ago
2007
Inverse Reinforcement Learning (IRL) is the problem of learning the reward function underlying a Markov Decision Process given the dynamics of the system and the behaviour of an e...
186
click to vote
ICMLA
2008
15 years 8 months ago
2008
In reinforcement learning, it is a common practice to map the state(-action) space to a different one using basis functions. This transformation aims to represent the input data i...
188
click to vote
KBS
2002
15 years 6 months ago
2002
In this paper, a hybrid learning approach named HDT is proposed. HDT simulates human reasoning by using symbolic learning to do qualitative analysis and using neural learning to d...
191
click to vote
ICRA
2008
IEEE
16 years 1 months ago
2008
IEEE
Abstract— Learning inverse kinematics has long been fascinating the robot learning community. While humans acquire this transformation to complicated tool spaces with ease, it is...
175
click to vote
CHI
2004
ACM
16 years 7 months ago
2004
ACM
Many studies have been conducted on supporting communication in home and office spaces, but relatively few studies have explored supporting communication in large-scale public spa...