@inproceedings{c90a23ad9bf04d0c8a5861d19e229c4d,
title = "Generalised discount functions applied to a Monte-Carlo AL implementation",
abstract = "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 an informed agent in a simple M DP. We experimentally reproduce a number of theoretical results, and discuss some related subtleties. It was found that the agent's behaviour followed what is expected theoretically, assuming appropriate parameters were chosen for the Monte-Carlo Tree Search (MOTS) planning algorithm.",
author = "Sean Lamont and John Aslanides and Jan Leike and Marcus Hutter",
note = "Publisher Copyright: {\textcopyright} Copyright 2017, International Foundation for Autonomous Agents and Multiagent Systems (www.ifaamas.org). All rights reserved.; 16th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2017 ; Conference date: 08-05-2017 Through 12-05-2017",
year = "2017",
language = "English",
series = "Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS",
publisher = "International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS)",
pages = "1589--1591",
editor = "Edmund Durfee and Michael Winikoff and Kate Larson and Sanmay Das",
booktitle = "16th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2017",
address = "United States",
}