16 search results - page 1 / 4 » Analyzing feature generation for value-function approximatio... |
ICAI
2009
14 years 7 months ago
2009
- 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...
ICML
2007
IEEE
15 years 10 months ago
2007
IEEE
We analyze a simple, Bellman-error-based approach to generating basis functions for valuefunction approximation. We show that it generates orthogonal basis functions that provably...
ESANN
2004
14 years 11 months ago
2004
Several reinforcement-learning techniques have already been applied to the Acrobot control problem, using linear function approximators to estimate the value function. In this pape...
AIPS
2004
14 years 11 months ago
2004
Approximate linear programming (ALP) offers a promising framework for solving large factored Markov decision processes (MDPs) with both discrete and continuous states. Successful ...
ICML
2005
IEEE
15 years 10 months ago
2005
IEEE
This paper presents a novel framework called proto-reinforcement learning (PRL), based on a mathematical model of a proto-value function: these are task-independent basis function...