5075 search results - page 189 / 1015 » Convergence |
144
click to vote
NIPS
2007
15 years 6 months ago
2007
We present four new reinforcement learning algorithms based on actor-critic and natural-gradient ideas, and provide their convergence proofs. Actor-critic reinforcement learning m...
136
Voted
WCE
2007
15 years 5 months ago
2007
—In this paper, we analyze the bounds of the fixed common step-size parameter GMDFµ for the generalized multidelay adaptive filter (GMDF). Frequency domain adaptive filters are ...
138
click to vote
AUTOMATICA
2008
15 years 4 months ago
2008
In this paper, a method for the performance assessment of a variable-gain control design for optical storage drives is proposed. The variablegain strategy is used to overcome well...
145
Voted
CORR
2010
Springer
15 years 4 months ago
2010
Springer
In this paper, we consider the problem of planning and learning in the infinite-horizon discounted-reward Markov decision problems. We propose a novel iterative direct policysearc...
168
click to vote
CORR
2008
Springer
15 years 4 months ago
2008
Springer
The design of sensor networks capable of reaching a consensus on a globally optimal decision test, without the need for a fusion center, is a problem that has received considerable...