1454 search results - page 171 / 291 » Learning with cost intervals |
172
click to vote
IROS
2008
IEEE
16 years 17 days ago
2008
IEEE
— High performance and compliant robot control requires accurate dynamics models which cannot be obtained analytically for sufficiently complex robot systems. In such cases, mac...
124
click to vote
ATAL
2007
Springer
16 years 10 days ago
2007
Springer
A MAS architecture consisting of service centers is proposed. Within each service center, a mediator coordinates service delivery by allocating individual tasks to corresponding t...
144
Voted
GECCO
2009
Springer
15 years 10 months ago
2009
Springer
Typical domains used in machine learning analyses only partially cover the complexity space, remaining a large proportion of problem difficulties that are not tested. Since the ac...
179
click to vote
GECCO
2010
Springer
15 years 9 months ago
2010
Springer
Shaping functions can be used in multi-task reinforcement learning (RL) to incorporate knowledge from previously experienced tasks to speed up learning on a new task. So far, rese...
143
click to vote
ATAL
2008
Springer
15 years 8 months ago
2008
Springer
The goal of Reinforcement learning (RL) is to maximize reward (minimize cost) in a Markov decision process (MDP) without knowing the underlying model a priori. RL algorithms tend ...