Skip navigation
Skip navigation

Feature reinforcement learning in practice

Nguyen, Phuong; Sunehag, Peter; Hutter, Marcus

Description

Following a recent surge in using history-based methods for resolving perceptual aliasing in reinforcement learning, we introduce an algorithm based on the feature reinforcement learning framework called ΦMDP [13]. To create a practical algorithm we devise a stochastic search procedure for a class of context trees based on parallel tempering and a specialized proposal distribution. We provide the first empirical evaluation for ΦMDP. Our proposed algorithm achieves superior performance to the...[Show more]

CollectionsANU Research Publications
Date published: 2011-09
Type: Conference paper
URI: http://hdl.handle.net/1885/14811
DOI: 10.1007/978-3-642-29946-9_10

Download

File Description SizeFormat Image
Nguyen et al Feature Reinforcement Learning in Practice 2011.pdf336.71 kBAdobe PDFThumbnail


Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.

Updated:  12 November 2018/ Responsible Officer:  University Librarian/ Page Contact:  Library Systems & Web Coordinator