A Novel Reward Shaping Function for Single-Player Mahjong

A Novel Reward Shaping Function for Single-Player Mahjong

Mahjong is a complex game with an intractably large state space with extremely sparse rewards, which poses challenges to develop an agent to play Mahjong. To overcome this, the ShangTing function was adopted as a reward shaping function. This was combined with a forward-search algorithm to create an...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2023-05
Hauptverfasser: Chen, Kai Jun, Lai, Lok Him, Zi Iun Lai
Format: Artikel
Sprache:eng
Schlagworte:
Games
Search algorithms
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Chen, Kai Jun
Lai, Lok Him
Zi Iun Lai
description Mahjong is a complex game with an intractably large state space with extremely sparse rewards, which poses challenges to develop an agent to play Mahjong. To overcome this, the ShangTing function was adopted as a reward shaping function. This was combined with a forward-search algorithm to create an agent capable of completing a winning hand in Single-player Mahjong (an average of 35 actions over 10,000 games). To increase performance, we propose a novel bonus reward shaping function, which assigns higher relative values to synergistic Mahjong hands. In a simulated 1-v-1 battle, usage of the new reward function outperformed the default ShangTing function, winning an average of $1.37 over 1000 games.
format Article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2811365634</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2811365634</sourcerecordid><originalsourceid>FETCH-proquest_journals_28113656343</originalsourceid><addsrcrecordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mSwdFTwyy9LzVEISi1PLEpRCM5ILMjMS1dwK81LLsnMz1NIyy9SCAaK5KTqBuQkVqYWKfgmZmTl56XzMLCmJeYUp_JCaW4GZTfXEGcP3YKi_MLS1OKS-Kz80qI8oFS8kYWhobGZqZmxiTFxqgAb9zWt</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2811365634</pqid></control><display><type>article</type><title>A Novel Reward Shaping Function for Single-Player Mahjong</title><source>Freely Accessible Journals</source><creator>Chen, Kai Jun ; Lai, Lok Him ; Zi Iun Lai</creator><creatorcontrib>Chen, Kai Jun ; Lai, Lok Him ; Zi Iun Lai</creatorcontrib><description>Mahjong is a complex game with an intractably large state space with extremely sparse rewards, which poses challenges to develop an agent to play Mahjong. To overcome this, the ShangTing function was adopted as a reward shaping function. This was combined with a forward-search algorithm to create an agent capable of completing a winning hand in Single-player Mahjong (an average of 35 actions over 10,000 games). To increase performance, we propose a novel bonus reward shaping function, which assigns higher relative values to synergistic Mahjong hands. In a simulated 1-v-1 battle, usage of the new reward function outperformed the default ShangTing function, winning an average of $1.37 over 1000 games.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Games ; Search algorithms</subject><ispartof>arXiv.org, 2023-05</ispartof><rights>2023. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>776,780</link.rule.ids></links><search><creatorcontrib>Chen, Kai Jun</creatorcontrib><creatorcontrib>Lai, Lok Him</creatorcontrib><creatorcontrib>Zi Iun Lai</creatorcontrib><title>A Novel Reward Shaping Function for Single-Player Mahjong</title><title>arXiv.org</title><description>Mahjong is a complex game with an intractably large state space with extremely sparse rewards, which poses challenges to develop an agent to play Mahjong. To overcome this, the ShangTing function was adopted as a reward shaping function. This was combined with a forward-search algorithm to create an agent capable of completing a winning hand in Single-player Mahjong (an average of 35 actions over 10,000 games). To increase performance, we propose a novel bonus reward shaping function, which assigns higher relative values to synergistic Mahjong hands. In a simulated 1-v-1 battle, usage of the new reward function outperformed the default ShangTing function, winning an average of $1.37 over 1000 games.</description><subject>Games</subject><subject>Search algorithms</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>BENPR</sourceid><recordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mSwdFTwyy9LzVEISi1PLEpRCM5ILMjMS1dwK81LLsnMz1NIyy9SCAaK5KTqBuQkVqYWKfgmZmTl56XzMLCmJeYUp_JCaW4GZTfXEGcP3YKi_MLS1OKS-Kz80qI8oFS8kYWhobGZqZmxiTFxqgAb9zWt</recordid><startdate>20230506</startdate><enddate>20230506</enddate><creator>Chen, Kai Jun</creator><creator>Lai, Lok Him</creator><creator>Zi Iun Lai</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PHGZM</scope><scope>PHGZT</scope><scope>PIMPY</scope><scope>PKEHL</scope><scope>PQEST</scope><scope>PQGLB</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20230506</creationdate><title>A Novel Reward Shaping Function for Single-Player Mahjong</title><author>Chen, Kai Jun ; Lai, Lok Him ; Zi Iun Lai</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_28113656343</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Games</topic><topic>Search algorithms</topic><toplevel>online_resources</toplevel><creatorcontrib>Chen, Kai Jun</creatorcontrib><creatorcontrib>Lai, Lok Him</creatorcontrib><creatorcontrib>Zi Iun Lai</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>ProQuest Central (New)</collection><collection>ProQuest One Academic (New)</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Middle East (New)</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Applied &amp; Life Sciences</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Chen, Kai Jun</au><au>Lai, Lok Him</au><au>Zi Iun Lai</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>A Novel Reward Shaping Function for Single-Player Mahjong</atitle><jtitle>arXiv.org</jtitle><date>2023-05-06</date><risdate>2023</risdate><eissn>2331-8422</eissn><abstract>Mahjong is a complex game with an intractably large state space with extremely sparse rewards, which poses challenges to develop an agent to play Mahjong. To overcome this, the ShangTing function was adopted as a reward shaping function. This was combined with a forward-search algorithm to create an agent capable of completing a winning hand in Single-player Mahjong (an average of 35 actions over 10,000 games). To increase performance, we propose a novel bonus reward shaping function, which assigns higher relative values to synergistic Mahjong hands. In a simulated 1-v-1 battle, usage of the new reward function outperformed the default ShangTing function, winning an average of $1.37 over 1000 games.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2023-05
issn 2331-8422
language eng
recordid cdi_proquest_journals_2811365634
source Freely Accessible Journals
subjects Games
Search algorithms
title A Novel Reward Shaping Function for Single-Player Mahjong
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-19T02%3A25%3A08IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=A%20Novel%20Reward%20Shaping%20Function%20for%20Single-Player%20Mahjong&rft.jtitle=arXiv.org&rft.au=Chen,%20Kai%20Jun&rft.date=2023-05-06&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2811365634%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2811365634&rft_id=info:pmid/&rfr_iscdi=true