Sciweavers

CDC
2010
IEEE
160views Control Systems» more  CDC 2010»
12 years 10 months ago
Adaptive bases for Q-learning
Abstract-- We consider reinforcement learning, and in particular, the Q-learning algorithm in large state and action spaces. In order to cope with the size of the spaces, a functio...
Dotan Di Castro, Shie Mannor
CORR
2010
Springer
204views Education» more  CORR 2010»
13 years 2 months ago
Predictive State Temporal Difference Learning
We propose a new approach to value function approximation which combines linear temporal difference reinforcement learning with subspace identification. In practical applications...
Byron Boots, Geoffrey J. Gordon
TNN
2008
181views more  TNN 2008»
13 years 3 months ago
Optimized Approximation Algorithm in Neural Networks Without Overfitting
In this paper, an optimized approximation algorithm (OAA) is proposed to address the overfitting problem in function approximation using neural networks (NNs). The optimized approx...
Yinyin Liu, Janusz A. Starzyk, Zhen Zhu
TNN
2008
119views more  TNN 2008»
13 years 3 months ago
Selecting Useful Groups of Features in a Connectionist Framework
Abstract--Suppose for a given classification or function approximation (FA) problem data are collected using sensors. From the output of the th sensor, features are extracted, ther...
Debrup Chakraborty, Nikhil R. Pal
TEC
2008
115views more  TEC 2008»
13 years 3 months ago
Function Approximation With XCS: Hyperellipsoidal Conditions, Recursive Least Squares, and Compaction
An important strength of learning classifier systems (LCSs) lies in the combination of genetic optimization techniques with gradient-based approximation techniques. The chosen app...
Martin V. Butz, Pier Luca Lanzi, Stewart W. Wilson
SCL
2008
109views more  SCL 2008»
13 years 3 months ago
A note on linear function approximation using random projections
ABSTRACT: Linear function approximations based on random projections are proposed and justified for a class of fixed point and minimization problems. KEY WORDS: random projections,...
Kishor Barman, Vivek S. Borkar
CORR
2010
Springer
119views Education» more  CORR 2010»
13 years 3 months ago
Dynamic Policy Programming
In this paper, we consider the problem of planning and learning in the infinite-horizon discounted-reward Markov decision problems. We propose a novel iterative direct policysearc...
Mohammad Gheshlaghi Azar, Hilbert J. Kappen
GECCO
2008
Springer
131views Optimization» more  GECCO 2008»
13 years 4 months ago
Self-adaptive mutation in XCSF
Recent advances in XCS technology have shown that selfadaptive mutation can be highly useful to speed-up the evolutionary progress in XCS. Moreover, recent publications have shown...
Martin V. Butz, Patrick O. Stalph, Pier Luca Lanzi
GECCO
2008
Springer
123views Optimization» more  GECCO 2008»
13 years 4 months ago
Hierarchical evolution of linear regressors
We propose an algorithm for function approximation that evolves a set of hierarchical piece-wise linear regressors. The algorithm, named HIRE-Lin, follows the iterative rule learn...
Francesc Teixidó-Navarro, Albert Orriols-Pu...
WSC
2004
13 years 5 months ago
Function-Approximation-Based Importance Sampling for Pricing American Options
Monte Carlo simulation techniques that use function approximations have been successfully applied to approximately price multi-dimensional American options. However, for many pric...
Nomesh Bolia, Sandeep Juneja, Paul Glasserman