Sciweavers

208 search results - page 1 / 42
» Constructing basis functions from directed graphs for value ...
Sort
View
ICML
2007
IEEE
14 years 5 months ago
Constructing basis functions from directed graphs for value function approximation
Basis functions derived from an undirected graph connecting nearby samples from a Markov decision process (MDP) have proven useful for approximating value functions. The success o...
Jeffrey Johns, Sridhar Mahadevan
AAAI
2007
13 years 7 months ago
Compact Spectral Bases for Value Function Approximation Using Kronecker Factorization
A new spectral approach to value function approximation has recently been proposed to automatically construct basis functions from samples. Global basis functions called proto-val...
Jeffrey Johns, Sridhar Mahadevan, Chang Wang
ICAI
2009
13 years 2 months ago
On the Construction of Initial Basis Function for Efficient Value Function Approximation
- We address the issues of improving the feature generation methods for the value-function approximation and the state space approximation. We focus the improvement of feature gene...
Chung-Cheng Chiu, Kuan-Ta Chen
ICML
2006
IEEE
13 years 10 months ago
Automatic basis function construction for approximate dynamic programming and reinforcement learning
We address the problem of automatically constructing basis functions for linear approximation of the value function of a Markov Decision Process (MDP). Our work builds on results ...
Philipp W. Keller, Shie Mannor, Doina Precup
ICML
2007
IEEE
14 years 5 months ago
Learning state-action basis functions for hierarchical MDPs
This paper introduces a new approach to actionvalue function approximation by learning basis functions from a spectral decomposition of the state-action manifold. This paper exten...
Sarah Osentoski, Sridhar Mahadevan