4013 search results - page 482 / 803 » computer 2002 |
146
click to vote
ML
2002
ACM
15 years 5 months ago
2002
ACM
Solving in an efficient manner many different optimal control tasks within the same underlying environment requires decomposing the environment into its computationally elemental ...
149
click to vote
ML
2002
ACM
15 years 5 months ago
2002
ACM
We present new algorithms for reinforcement learning, and prove that they have polynomial bounds on the resources required to achieve near-optimal return in general Markov decisio...
175
click to vote
ML
2002
ACM
15 years 5 months ago
2002
ACM
We provide an analytical comparison between discounted and average reward temporal-difference (TD) learning with linearly parameterized approximations. We first consider the asympt...
151
Voted
MP
2002
15 years 5 months ago
2002
The efficient solution of large-scale linear and nonlinear optimization problems may require exploiting any special structure in them in an efficient manner. We describe and analy...
131
click to vote
MP
2002
15 years 5 months ago
2002
In this paper we address a general Goal Programming problem with linear objectives, convex constraints, and an arbitrary componentwise nondecreasing norm to aggregate deviations w...