Bayesian Learning of Recursively Factored Environments. Bellemare, M, Veness, J, & Bowling, M webdocs.cs.ualberta.ca.
abstract   bibtex   
Abstract Model-based reinforcement learning techniques have historically encountered a number of difficulties scaling up to large observation spaces. One promising approach has been to decompose the model learning task into a number of smaller, more manageable.
@Article{Bellemare,
author = {Bellemare, M and Veness, J and Bowling, M}, 
title = {Bayesian Learning of Recursively Factored Environments}, 
journal = {webdocs.cs.ualberta.ca}, 
volume = {}, 
number = {}, 
pages = {}, 
year = {}, 
abstract = {Abstract Model-based reinforcement learning techniques have historically encountered a number of difficulties scaling up to large observation spaces. One promising approach has been to decompose the model learning task into a number of smaller, more manageable.}, 
location = {}, 
keywords = {}}

Downloads: 0