- 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...
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...
Ronald Parr, Christopher Painter-Wakefield, Lihong...
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...
Approximate linear programming (ALP) offers a promising framework for solving large factored Markov decision processes (MDPs) with both discrete and continuous states. Successful ...
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...