1566 search results - page 15 / 314 » Planning and learning together |
ICMAS
2000
15 years 1 months ago
2000
This paper describes a multiagent variant of Dyna-Q called M-Dyna-Q. Dyna-Q is an integrated single-agent framework for planning, reacting, and learning. Like DynaQ, M-Dyna-Q empl...
ECML
2005
Springer
15 years 5 months ago
2005
Springer
Abstract. Classical planning domain representations assume all the objects from one type are exactly the same. But when solving problems in the real world systems, the execution of...
ICRA
2009
IEEE
15 years 6 months ago
2009
IEEE
Abstract— Robotic manipulation is important for real, physical world applications. General Purpose manipulation with a robot (eg. delivering dishes, opening doors with a key, etc...
ICRA
2009
IEEE
14 years 9 months ago
2009
IEEE
For vehicles navigating initially unknown cluttered environments, current state-of-the-art planning algorithms are able to plan and re-plan dynamically-feasible paths efficiently a...
ATAL
2010
Springer
15 years 26 days ago
2010
Springer
An important drawback to the popular Belief, Desire, and Intentions (BDI) paradigm is that such systems include no element of learning from experience. In particular, the so-calle...