250 search results - page 28 / 50 » Learning action effects in partially observable domains |
AAAI
2007
14 years 12 months ago
2007
Planning under uncertainty involves two distinct sources of uncertainty: uncertainty about the effects of actions and uncertainty about the current state of the world. The most wi...
AIIA
2005
Springer
15 years 3 months ago
2005
Springer
Abstract. In order to have a robotic system able to effectively learn by imitation, and not merely reproduce the movements of a human teacher, the system should have the capabiliti...
88
Voted
AIPS
2003
14 years 11 months ago
2003
There have been several proposals for expressing planning problems with different forms of uncertainty, including nondeterminism and partial observability. In this paper we invest...
ICRA
2010
IEEE
14 years 8 months ago
2010
IEEE
— Reinforcement learning (RL) algorithms have long been promising methods for enabling an autonomous robot to improve its behavior on sequential decision-making tasks. The obviou...
AIPS
2009
14 years 10 months ago
2009
Finite-state and memoryless controllers are simple action selection mechanisms widely used in domains such as videogames and mobile robotics. Memoryless controllers stand for func...