446 search results - page 21 / 90 » Convergence and rate of convergence of a simple ant model |
ECAI
2008
Springer
14 years 11 months ago
2008
Springer
In this paper, we propose a policy gradient reinforcement learning algorithm to address transition-independent Dec-POMDPs. This approach aims at implicitly exploiting the locality...
FSTTCS
2008
Springer
14 years 10 months ago
2008
Springer
Abstract. We study the decision theory of a maximally risk-averse investor — one whose objective, in the face of stochastic uncertainties, is to minimize the probability of ever ...
COLT
2004
Springer
15 years 3 months ago
2004
Springer
Abstract. We study two boosting algorithms, Coordinate Ascent Boosting and Approximate Coordinate Ascent Boosting, which are explicitly designed to produce maximum margins. To deri...
COLT
2008
Springer
14 years 11 months ago
2008
Springer
Standard no-internal-regret (NIR) algorithms compute a fixed point of a matrix, and hence typically require O(n3 ) run time per round of learning, where n is the dimensionality of...
TIT
2011
14 years 4 months ago
2011
—This work first presents a general technique to compute tight upper and lower bounds on the information rate of a multiuser Rayleigh fading channel with no Channel State Inform...