41 search results - page 5 / 9 » How to learn accurate grid maps with a humanoid |
168
click to vote
IROS
2008
IEEE
16 years 1 months ago
2008
IEEE
— Legged robots require accurate models of their environment in order to plan and execute paths. We present a probabilistic technique based on Gaussian processes that allows terr...
167
click to vote
PKDD
2007
Springer
16 years 22 days ago
2007
Springer
Abstract. This paper shows how multi-dimensional functions, describing the operation of complex equipment, can be learned. The functions are points in a shape space, each produced ...
192
click to vote
NIPS
1996
15 years 8 months ago
1996
Dynamic Programming, Q-learning and other discrete Markov Decision Process solvers can be applied to continuous d-dimensional state-spaces by quantizing the state space into an arr...
173
click to vote
AAAI
2004
15 years 8 months ago
2004
This paper deals with automatically learning the spatial distribution of a set of images. That is, given a sequence of images acquired from well-separated locations, how can they ...
165
click to vote
ECML
2006
Springer
15 years 10 months ago
2006
Springer
Abstract. Approximate Policy Iteration (API) is a reinforcement learning paradigm that is able to solve high-dimensional, continuous control problems. We propose to exploit API for...