548 search results - page 12 / 110 » A New Way to Introduce Knowledge into Reinforcement Learning |
104
click to vote
CORR
2012
Springer
13 years 5 months ago
2012
Springer
Bayesian priors offer a compact yet general means of incorporating domain knowledge into many learning tasks. The correctness of the Bayesian analysis and inference, however, lar...
ICRA
2009
IEEE
15 years 4 months ago
2009
IEEE
— To address the difficulty of designing a controller for complex visual-servoing tasks, two learning-based uncalibrated approaches are introduced. The first method starts by b...
83
Voted
IDEAL
2007
Springer
15 years 3 months ago
2007
Springer
Recently researchers have introduced methods to develop reusable knowledge in reinforcement learning (RL). In this paper, we define simple principles to combine skills in reinforce...
105
click to vote
HIS
2004
14 years 11 months ago
2004
: This work presents a new hybrid neuro-fuzzy model for automatic learning of actions taken by agents. The main objective of this new model is to provide an agent with intelligence...
ICML
2000
IEEE
15 years 10 months ago
2000
IEEE
This paper discusses theoretical and experimental aspects of gradient-based approaches to the direct optimization of policy performance in controlled ??? ?s. We introduce ??? ?, a...