Sciweavers

3256 search results - page 76 / 652
» Learning Linear Transformations
Sort
View
COLT
2001
Springer
14 years 7 days ago
Learning Rates for Q-Learning
In this paper we derive convergence rates for Q-learning. We show an interesting relationship between the convergence rate and the learning rate used in Q-learning. For a polynomi...
Eyal Even-Dar, Yishay Mansour
CP
2000
Springer
14 years 2 days ago
Linear Formulation of Constraint Programming Models and Hybrid Solvers
Constraint programming offers a variety of modeling objects such as logical and global constraints, that lead to concise and clear models for expressing combinatorial optimization...
Philippe Refalo
AAIM
2006
Springer
94views Algorithms» more  AAIM 2006»
13 years 11 months ago
Linear Programming Polytope and Algorithm for Mean Payoff Games
We investigate LP-polytopes generated by mean payoff games and their properties, including the existence of tight feasible solutions of bounded size. We suggest a new associated al...
Ola Svensson, Sergei G. Vorobyov
APAL
2008
67views more  APAL 2008»
13 years 7 months ago
Proof nets sequentialisation in multiplicative linear logic
Abstract. We provide an alternative proof of the sequentialisation theorem for proof nets of multiplicative linear logic. Namely, we show how a proof net can be transformed into a ...
Paolo Di Giamberardino, Claudia Faggian
PR
2006
145views more  PR 2006»
13 years 7 months ago
Gait recognition using linear time normalization
We present a novel system for gait recognition. Identity recognition and verification are based on the matching of linearly timenormalized gait walking cycles. A novel feature ext...
Nikolaos V. Boulgouris, Konstantinos N. Platanioti...