Sciweavers

1674 search results - page 17 / 335
» Learning Actions From the Web
Sort
View
ECML
2006
Springer
15 years 1 months ago
Task-Driven Discretization of the Joint Space of Visual Percepts and Continuous Actions
We target the problem of closed-loop learning of control policies that map visual percepts to continuous actions. Our algorithm, called Reinforcement Learning of Joint Classes (RLJ...
Sébastien Jodogne, Justus H. Piater
AAAI
2006
14 years 11 months ago
Walk the Talk: Connecting Language, Knowledge, and Action in Route Instructions
Following verbal route instructions requires knowledge of language, space, action and perception. We present MARCO, an agent that follows free-form, natural language route instruc...
Matt MacMahon, Brian Stankiewicz, Benjamin Kuipers
AI
2001
Springer
15 years 2 months ago
Imitation and Reinforcement Learning in Agents with Heterogeneous Actions
Reinforcement learning techniques are increasingly being used to solve di cult problems in control and combinatorial optimization with promising results. Implicit imitation can acc...
Bob Price, Craig Boutilier
BSN
2011
IEEE
233views Sensor Networks» more  BSN 2011»
13 years 9 months ago
Compressive Sensing of Neural Action Potentials Using a Learned Union of Supports
—Wireless neural recording systems are subject to stringent power consumption constraints to support long-term recordings and to allow for implantation inside the brain. In this ...
Zainul Charbiwala, Vaibhav Karkare, Sarah Gibson, ...
80
Voted
WEBNET
2000
14 years 11 months ago
To Measure or not to measure: Why web usability is different from traditional usability
: Web usability is a common term used in discussions of WWW (World Wide Web). This is definitely important, as more and more web sites are frequently visited and have great impact ...
Charlotte Olsson