Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/87236
Title: HogRider: Champion agent of Microsoft Malmo collaborative AI challenge
Authors: Xiong, Yanhai
Chen, Haipeng
Zhao, Mengchen
An, Bo
Keywords: Opponent Modeling
Multiagent Learning
Issue Date: 2018
Source: Xiong, Y., Chen, H., Zhao, M., & An, B. (2018). HogRider: Champion agent of Microsoft Malmo collaborative AI challenge. The Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18), 4767-4774.
Abstract: It has been an open challenge for self-interested agents to make optimal sequential decisions in complex multiagent systems, where agents might achieve higher utility via collaboration. The Microsoft Malmo Collaborative AI Challenge (MCAC), which is designed to encourage research relating to various problems in Collaborative AI, takes the form of a Minecraft mini-game where players might work together to catch a pig or deviate from cooperation, for pursuing high scores to win the challenge. Various characteristics, such as complex interactions among agents, uncertainties, sequential decision making and limited learning trials all make it extremely challenging to find effective strategies. We present HogRider - the champion agent of MCAC in 2017 out of 81 teams from 26 countries. One key innovation of HogRider is a generalized agent type hypothesis framework to identify the behavior model of the other agents, which is demonstrated to be robust to observation uncertainty. On top of that, a second key innovation is a novel Q-learning approach to learn effective policies against each type of the collaborating agents. Various ideas are proposed to adapt traditional Qlearning to handle complexities in the challenge, including state-action abstraction to reduce problem scale, a warm start approach using human reasoning for addressing limited learning trials, and an active greedy strategy to balance exploitation-exploration. Challenge results show that HogRider outperforms all the other teams by a significant edge, in terms of both optimality and stability.
URI: https://hdl.handle.net/10356/87236
http://hdl.handle.net/10220/44897
URL: https://www.aaai.org/ocs/index.php/AAAI/AAAI18/paper/view/16385
Rights: © 2018 Association for the Advancement of Artificial Intelligence. This is the author created version of a work that has been peer reviewed and accepted for publication by The Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18), Association for the Advancement of Artificial Intelligence. It incorporates referee’s comments but changes resulting from the publishing process, such as copyediting, structural formatting, may not be reflected in this document. The published version is available at: [https://www.aaai.org/ocs/index.php/AAAI/AAAI18/paper/view/16385].
Fulltext Permission: open
Fulltext Availability: With Fulltext
Appears in Collections:IGS Conference Papers

Files in This Item:
File Description SizeFormat 
AAAI18_Malmo.pdf1.95 MBAdobe PDFThumbnail
View/Open

Page view(s) 5

928
Updated on Apr 19, 2021

Download(s) 10

374
Updated on Apr 19, 2021

Google ScholarTM

Check

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.