Sciweavers

226 search results - page 1 / 46
» A Monte-Carlo AIXI Approximation
Sort
View
JAIR
2011
187views more  JAIR 2011»
13 years 2 months ago
A Monte-Carlo AIXI Approximation
This paper describes a computationally feasible approximation to the AIXI agent, a universal reinforcement learning agent for arbitrary environments. AIXI is scaled down in two ke...
Joel Veness, Kee Siong Ng, Marcus Hutter, William ...
AGI
2008
13 years 8 months ago
A computational approximation to the AIXI model
Universal induction solves in principle the problem of choosing a prior to achieve optimal inductive inference. The AIXI theory, which combines control theory and universal induct...
Sergey Pankov
AAAI
2010
13 years 8 months ago
Reinforcement Learning via AIXI Approximation
This paper introduces a principled approach for the design of a scalable general reinforcement learning agent. This approach is based on a direct approximation of AIXI, a Bayesian...
Joel Veness, Kee Siong Ng, Marcus Hutter, David Si...
ICCS
2007
Springer
14 years 1 months ago
Complexity of Monte Carlo Algorithms for a Class of Integral Equations
In this work we study the computational complexity of a class of grid Monte Carlo algorithms for integral equations. The idea of the algorithms consists in an approximation of the ...
Ivan Dimov, Rayna Georgieva
ML
2007
ACM
192views Machine Learning» more  ML 2007»
13 years 6 months ago
Annealing stochastic approximation Monte Carlo algorithm for neural network training
We propose a general-purpose stochastic optimization algorithm, the so-called annealing stochastic approximation Monte Carlo (ASAMC) algorithm, for neural network training. ASAMC c...
Faming Liang