Sciweavers

2934 search results - page 36 / 587
» Hypothesis Spaces for Learning
Sort
View
IJAIT
2008
146views more  IJAIT 2008»
13 years 11 months ago
Learning to Behave in Space: a Qualitative Spatial Representation for Robot Navigation with Reinforcement Learning
ion mechanism to create a representation of space consisting of the circular order of detected landmarks and the relative position of walls towards the agent's moving directio...
Lutz Frommberger
ICML
2007
IEEE
14 years 11 months ago
Reinforcement learning by reward-weighted regression for operational space control
Many robot control problems of practical importance, including operational space control, can be reformulated as immediate reward reinforcement learning problems. However, few of ...
Jan Peters, Stefan Schaal
ISRR
2005
Springer
135views Robotics» more  ISRR 2005»
14 years 4 months ago
Mimetic Communication Theory for Humanoid Robots Interacting with Humans
d a human. The meta proto-symbols are a little more abstract analogy of the proto-symbols and recognize/generate the relationship of the two. A hypothesis is then proposed as the p...
Yoshihiko Nakamura, Wataru Takano, Katsu Yamane
ALT
2000
Springer
14 years 7 months ago
Learning Recursive Concepts with Anomalies
This paper provides a systematic study of inductive inference of indexable concept classes in learning scenarios in which the learner is successful if its final hypothesis describ...
Gunter Grieser, Steffen Lange, Thomas Zeugmann
AII
1992
14 years 2 months ago
Learning from Multiple Sources of Inaccurate Data
Most theoretical models of inductive inference make the idealized assumption that the data available to a learner is from a single and accurate source. The subject of inaccuracies ...
Ganesh Baliga, Sanjay Jain, Arun Sharma