Sciweavers

6 search results - page 1 / 2
» Robot Weightlifting By Direct Policy Search
Sort
View
IJCAI
2001
13 years 6 months ago
Robot Weightlifting By Direct Policy Search
This paper describes a method for structuring a robot motor learning task. By designing a suitably parameterized policy, we show that a simple search algorithm, along with biologi...
Michael T. Rosenstein, Andrew G. Barto
CCIA
2005
Springer
13 years 10 months ago
Direct Policy Search Reinforcement Learning for Robot Control
— This paper proposes a high-level Reinforcement Learning (RL) control system for solving the action selection problem of an autonomous robot. Although the dominant approach, whe...
Andres El-Fakdi, Marc Carreras, Narcís Palo...
ICRA
2005
IEEE
91views Robotics» more  ICRA 2005»
13 years 10 months ago
Learning to Steer on Winding Tracks Using Semi-Parametric Control Policies
— We present a semi-parametric control policy representation and use it to solve a series of nonholonomic control problems with input state spaces of up to 7 dimensions. A neares...
Kenneth Robert Alton, Michiel van de Panne
ICRA
2010
IEEE
136views Robotics» more  ICRA 2010»
13 years 2 months ago
Efficient planning under uncertainty for a target-tracking micro-aerial vehicle
A helicopter agent has to plan trajectories to track multiple ground targets from the air. The agent has partial information of each target's pose, and must reason about its u...
Ruijie He, Abraham Bachrach, Nicholas Roy
ICRA
2008
IEEE
123views Robotics» more  ICRA 2008»
13 years 11 months ago
Target-directed attention: Sequential decision-making for gaze planning
— It is widely agreed that efficient visual search requires the integration of target-driven top-down information and image-driven bottom-up information. Yet the problem of gaze...
Julia Vogel, Nando de Freitas