In this paper we assess the hypothesis that a strategy including information related to game-specific factors in a poker tournament performs better than one founded on hand strength knowledge alone. Specifically, we demonstrate that the use of information pertaining to opponents' prior actions, the stage of the tournament, one's chip stack size and seating position all contribute towards a statistically significant improvement in the number of tournaments won. Additionally, we test the hypothesis that a strategy which combines information from all the aforementioned factors performs better than one which employs only a single factor. We show that an evolutionary algorithm is successfully able to resolve conflicting signals from the specified factors, and that the resulting strategies are statistically stronger
{"title":"An Investigation into Tournament Poker Strategy using Evolutionary Algorithms","authors":"Richard G. Carter, John Levine","doi":"10.1109/CIG.2007.368087","DOIUrl":"https://doi.org/10.1109/CIG.2007.368087","url":null,"abstract":"In this paper we assess the hypothesis that a strategy including information related to game-specific factors in a poker tournament performs better than one founded on hand strength knowledge alone. Specifically, we demonstrate that the use of information pertaining to opponents' prior actions, the stage of the tournament, one's chip stack size and seating position all contribute towards a statistically significant improvement in the number of tournaments won. Additionally, we test the hypothesis that a strategy which combines information from all the aforementioned factors performs better than one which employs only a single factor. We show that an evolutionary algorithm is successfully able to resolve conflicting signals from the specified factors, and that the resulting strategies are statistically stronger","PeriodicalId":365269,"journal":{"name":"2007 IEEE Symposium on Computational Intelligence and Games","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123356477","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In the iterated prisoner's dilemma (IPD) game, players normally have access to their own history, without being able to communicate global information. In this paper, we introduce information sharing among players of the IPD game. During the co-evolutionary process, players obtain access, through information sharing, to the common strategy adopted by the majority of the population in the previous generation. An extra bit is added to the history portion in the strategy chromosome. This extra bit holds a value of 0 if the decisions to cooperate were greater than the decisions to defect in the last generation and 1 if otherwise. We show that information sharing alters the dynamics of the IPD game
{"title":"Information Sharing in the Iterated Prisoner's Dilemma Game","authors":"Ayman Ghoneim, H. Abbass, M. Barlow","doi":"10.1109/CIG.2007.368079","DOIUrl":"https://doi.org/10.1109/CIG.2007.368079","url":null,"abstract":"In the iterated prisoner's dilemma (IPD) game, players normally have access to their own history, without being able to communicate global information. In this paper, we introduce information sharing among players of the IPD game. During the co-evolutionary process, players obtain access, through information sharing, to the common strategy adopted by the majority of the population in the previous generation. An extra bit is added to the history portion in the strategy chromosome. This extra bit holds a value of 0 if the decisions to cooperate were greater than the decisions to defect in the last generation and 1 if otherwise. We show that information sharing alters the dynamics of the IPD game","PeriodicalId":365269,"journal":{"name":"2007 IEEE Symposium on Computational Intelligence and Games","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126443198","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
RoboCup soccer simulation features the challenges of a fully distributed multi-agent domain with continuous state and action spaces, partial observability, as well as noisy perception and action execution. While the application of machine learning techniques in this domain represents a promising idea in itself, the competitive character of RoboCup also evokes the desire to head for the development of learning algorithms that are more than just a proof of concept. In this paper, we report on our experiences and achievements in applying reinforcement learning (RL) methods in the scope of our Brainstormers competition team within the Simulation League of RoboCup during the past years
{"title":"On Experiences in a Complex and Competitive Gaming Domain: Reinforcement Learning Meets RoboCup","authors":"Martin A. Riedmiller, T. Gabel","doi":"10.1109/CIG.2007.368074","DOIUrl":"https://doi.org/10.1109/CIG.2007.368074","url":null,"abstract":"RoboCup soccer simulation features the challenges of a fully distributed multi-agent domain with continuous state and action spaces, partial observability, as well as noisy perception and action execution. While the application of machine learning techniques in this domain represents a promising idea in itself, the competitive character of RoboCup also evokes the desire to head for the development of learning algorithms that are more than just a proof of concept. In this paper, we report on our experiences and achievements in applying reinforcement learning (RL) methods in the scope of our Brainstormers competition team within the Simulation League of RoboCup during the past years","PeriodicalId":365269,"journal":{"name":"2007 IEEE Symposium on Computational Intelligence and Games","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128483549","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：