81 search results - page 14 / 17 » An extended policy gradient algorithm for robot task learnin... |
ATAL
2005
Springer
14 years 2 months ago
2005
Springer
Reinforcement learning problems are commonly tackled with temporal difference methods, which use dynamic programming and statistical sampling to estimate the long-term value of ta...
FLAIRS
2006
13 years 10 months ago
2006
RUPART1 is a hybrid robot control system for navigating a real-world, academic building. Hybrid robot control systems provide robust low-level navigation together with strategic p...
CVPR
2006
IEEE
14 years 10 months ago
2006
IEEE
Edge detection is one of the most studied problems in computer vision, yet it remains a very challenging task. It is difficult since often the decision for an edge cannot be made ...
AROBOTS
1998
13 years 8 months ago
1998
Rogue is an architecture built on a real robot which provides algorithms for the integration of highlevel planning, low-level robotic execution, and learning. Rogue addresses succ...
ROBOCUP
2007
Springer
14 years 2 months ago
2007
Springer
Abstract. Two main challenges of robot action planning in real domains are uncertain action effects and dynamic environments. In this paper, an instance-based action model is lear...