109 search results - page 1 / 22 » Closing the loop: modelling action, perception and informati... |
AVI
1996
13 years 6 months ago
1996
Visual interfaces to computer systems are interactive. The cycle of visual interaction involves both visual perception and action. This paper examines formal models of interactive...
ECML
2006
Springer
13 years 8 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...
EH
2004
IEEE
13 years 8 months ago
2004
IEEE
Sensor evolution in nature aims at improving the acquisition of information from the environment and is intimately related with selection pressure towards adaptivity and robustnes...
ATAL
2010
Springer
13 years 5 months ago
2010
Springer
A central problem in artificial intelligence is to choose actions to maximize reward in a partially observable, uncertain environment. To do so, we must learn an accurate model of ...
JAIR
2007
13 years 4 months ago
2007
In this paper we present a general, flexible framework for learning mappings from images to actions by interacting with the environment. The basic idea is to introduce a feature-...