Skip navigation
Skip navigation

Generalised discount functions applied to a Monte-Carlo AL implementation

Lamont, Sean; Aslanides, John; Leike, Jan; Hutter, Marcus

Description

In recent years, work has been done to develop the theory of General Reinforcement Learning (GRL). However, there are no examples demonstrating the known results regarding generalised discounting. We have added to the GRL simulation platform (AIXIjs) the functionality to assign an agent arbitrary discount functions, and an environment which can be used to determine the effect of discounting on an agent's policy. Using this, we investigate how geometric, hyperbolic and power discounting affect...[Show more]

CollectionsANU Research Publications
Date published: 2017
Type: Conference paper
URI: http://hdl.handle.net/1885/205901
Source: Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS
Access Rights: Open Access via publisher website

Download

File Description SizeFormat Image
01_Lamont_Generalised_discount_functions_2017.pdf508.41 kBAdobe PDF    Request a copy


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

Updated:  19 May 2020/ Responsible Officer:  University Librarian/ Page Contact:  Library Systems & Web Coordinator