730 search results - page 28 / 146 » Learning for control from multiple demonstrations |
IMR
2003
Springer
15 years 4 months ago
2003
Springer
A Cartesian grid generation methodology is developed for unsteady control volume computational fluid dynamic (CFD) solvers. Arbitrary combinations and numbers of moving and statio...
203
click to vote
Publication
We generalise the problem of inverse reinforcement learning to multiple tasks, from multiple demonstrations. Each one may represent one expert trying to solve a different task, or ...
107
click to vote
ICRA
2006
IEEE
15 years 5 months ago
2006
IEEE
— Legged robots can, in principle, traverse a large variety of obstacles and terrains. In this paper, we describe a successful application of reinforcement learning to the proble...
IROS
2008
IEEE
15 years 6 months ago
2008
IEEE
— This paper proposes an optimal gait generation framework using virtual constraint and learning optimal control. In this method, firstly, we add a constraint by a virtual poten...
122
click to vote
JAIR
2007
14 years 11 months ago
2007
In this paper we present a general, flexible framework for learning mappings from images to actions by interacting with the environment. The basic idea is to introduce a feature-...