Sciweavers

3694 search results - page 16 / 739
» Stochastic complexity in learning
Sort
View
SIAMCO
2000
117views more  SIAMCO 2000»
13 years 7 months ago
The O.D.E. Method for Convergence of Stochastic Approximation and Reinforcement Learning
It is shown here that stability of the stochastic approximation algorithm is implied by the asymptotic stability of the origin for an associated ODE. This in turn implies convergen...
Vivek S. Borkar, Sean P. Meyn
JMLR
2010
148views more  JMLR 2010»
13 years 2 months ago
A Generalized Path Integral Control Approach to Reinforcement Learning
With the goal to generate more scalable algorithms with higher efficiency and fewer open parameters, reinforcement learning (RL) has recently moved towards combining classical tec...
Evangelos Theodorou, Jonas Buchli, Stefan Schaal
ATAL
2007
Springer
14 years 1 months ago
Advice taking in multiagent reinforcement learning
This paper proposes the β-WoLF algorithm for multiagent reinforcement learning (MARL) in the stochastic games framework that uses an additional “advice” signal to inform agen...
Michael Rovatsos, Alexandros Belesiotis
DEDS
2006
78views more  DEDS 2006»
13 years 7 months ago
The Equivalence between Ordinal Optimization in Deterministic Complex Problems and in Stochastic Simulation Problems
In the last decade ordinal optimization (OO) has been successfully applied in many stochastic simulation-based optimization problems (SP) and deterministic complex problems (DCP). ...
Yu-Chi Ho, Qing-Shan Jia, Qianchuan Zhao
GECCO
2007
Springer
162views Optimization» more  GECCO 2007»
14 years 1 months ago
Learning noise
In this paper we propose a genetic programming approach to learning stochastic models with unsymmetrical noise distributions. Most learning algorithms try to learn from noisy data...
Michael D. Schmidt, Hod Lipson