94 search results - page 14 / 19 » A Generalized Path Integral Control Approach to Reinforcemen... |
ICML
1994
IEEE
15 years 28 days ago
1994
IEEE
Compositional Q-Learning (CQ-L) (Singh 1992) is a modular approach to learning to performcomposite tasks made up of several elemental tasks by reinforcement learning. Skills acqui...
ML
2000
ACM
14 years 9 months ago
2000
ACM
This paper discusses a novel distributed adaptive algorithm and representation used to construct populations of adaptive Web agents. These InfoSpiders browse networked information ...
GECCO
2008
Springer
14 years 10 months ago
2008
Springer
Legged robots are useful in tasks such as search and rescue because they can effectively navigate on rugged terrain. However, it is difficult to design controllers for them that ...
ATAL
2008
Springer
14 years 11 months ago
2008
Springer
In this paper, we show how adaptive prototype optimization can be used to improve the performance of function approximation based on Kanerva Coding when solving largescale instanc...
NIPS
1993
14 years 10 months ago
1993
Dynamic programming provides a methodology to develop planners and controllers for nonlinear systems. However, general dynamic programming is computationally intractable. We have ...