Pub Date : 2016-12-01DOI: 10.1109/TCIAIG.2015.2464711
Wojciech Jaśkowski, M. Szubert
One weakness of coevolutionary algorithms observed in knowledge-free learning of strategies for adversarial games has been their poor scalability with respect to the number of parameters to learn. In this paper, we investigate to what extent this problem can be mitigated by using Covariance Matrix Adaptation Evolution Strategy, a powerful continuous optimization algorithm. In particular, we employ this algorithm in a competitive coevolutionary setup, denoting this setting as Co-CMA-ES. We apply it to learn position evaluation functions for the game of Othello and find out that, in contrast to plain (co)evolution strategies, Co-CMA-ES learns faster, finds superior game-playing strategies and scales better. Its advantages come out into the open especially for large parameter spaces of tens of hundreds of dimensions. For Othello, combining Co-CMA-ES with experimentally-tuned derandomized systematic n-tuple networks significantly improved the current state of the art. Our best strategy outperforms all the other Othello 1-ply players published to date by a large margin regardless of whether the round-robin tournament among them involves a fixed set of initial positions or the standard initial position but randomized opponents. These results show a large potential of CMA-ES-driven coevolution, which could be, presumably, exploited also in other games.
{"title":"Coevolutionary CMA-ES for Knowledge-Free Learning of Game Position Evaluation","authors":"Wojciech Jaśkowski, M. Szubert","doi":"10.1109/TCIAIG.2015.2464711","DOIUrl":"https://doi.org/10.1109/TCIAIG.2015.2464711","url":null,"abstract":"One weakness of coevolutionary algorithms observed in knowledge-free learning of strategies for adversarial games has been their poor scalability with respect to the number of parameters to learn. In this paper, we investigate to what extent this problem can be mitigated by using Covariance Matrix Adaptation Evolution Strategy, a powerful continuous optimization algorithm. In particular, we employ this algorithm in a competitive coevolutionary setup, denoting this setting as Co-CMA-ES. We apply it to learn position evaluation functions for the game of Othello and find out that, in contrast to plain (co)evolution strategies, Co-CMA-ES learns faster, finds superior game-playing strategies and scales better. Its advantages come out into the open especially for large parameter spaces of tens of hundreds of dimensions. For Othello, combining Co-CMA-ES with experimentally-tuned derandomized systematic n-tuple networks significantly improved the current state of the art. Our best strategy outperforms all the other Othello 1-ply players published to date by a large margin regardless of whether the round-robin tournament among them involves a fixed set of initial positions or the standard initial position but randomized opponents. These results show a large potential of CMA-ES-driven coevolution, which could be, presumably, exploited also in other games.","PeriodicalId":49192,"journal":{"name":"IEEE Transactions on Computational Intelligence and AI in Games","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/TCIAIG.2015.2464711","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"62593202","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}
Pub Date : 2016-12-01DOI: 10.1109/TCIAIG.2016.2601116
M. Buro, Santiago Ontañón, M. Preuss
{"title":"Guest Editorial Real-Time Strategy Games","authors":"M. Buro, Santiago Ontañón, M. Preuss","doi":"10.1109/TCIAIG.2016.2601116","DOIUrl":"https://doi.org/10.1109/TCIAIG.2016.2601116","url":null,"abstract":"","PeriodicalId":49192,"journal":{"name":"IEEE Transactions on Computational Intelligence and AI in Games","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82944783","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}
Pub Date : 2016-12-01DOI: 10.1109/TCIAIG.2015.2489159
Stephen G. Ware, R. Young
In this paper, we present The Best Laid Plans, an interactive narrative adventure game, and the planning technologies used to generate and adapt its story in real time. The game leverages computational models of intentionality and conflict when controlling the non-player characters (NPCs) to ensure they act believably and introduce challenge into the automatically generated narratives. We evaluate the game's ability to generate NPC behaviors that human players recognize as intentional and as conflicting with their plans. We demonstrate that players recognize these phenomena significantly more than in a control with no NPC actions and not significantly different from a control in which NPC actions are defined by a human author.
在本文中，我们将介绍互动叙事冒险游戏《The Best lay Plans》，以及用于实时生成和调整其故事的规划技术。在控制非玩家角色(npc)时，游戏利用了意向性和冲突的计算模型，以确保他们的行为可信，并在自动生成的叙述中引入挑战。我们评估游戏产生NPC行为的能力，这些NPC行为被人类玩家认为是故意的，并且与他们的计划相冲突。我们证明，比起没有NPC行动的控制，玩家更能识别这些现象，与由人类作者定义NPC行动的控制也没有明显区别。
{"title":"Intentionality and Conflict in The Best Laid Plans Interactive Narrative Virtual Environment","authors":"Stephen G. Ware, R. Young","doi":"10.1109/TCIAIG.2015.2489159","DOIUrl":"https://doi.org/10.1109/TCIAIG.2015.2489159","url":null,"abstract":"In this paper, we present The Best Laid Plans, an interactive narrative adventure game, and the planning technologies used to generate and adapt its story in real time. The game leverages computational models of intentionality and conflict when controlling the non-player characters (NPCs) to ensure they act believably and introduce challenge into the automatically generated narratives. We evaluate the game's ability to generate NPC behaviors that human players recognize as intentional and as conflicting with their plans. We demonstrate that players recognize these phenomena significantly more than in a control with no NPC actions and not significantly different from a control in which NPC actions are defined by a human author.","PeriodicalId":49192,"journal":{"name":"IEEE Transactions on Computational Intelligence and AI in Games","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/TCIAIG.2015.2489159","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"62593432","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}
Pub Date : 2016-12-01DOI: 10.1109/TCIAIG.2015.2414447
Johan Hagelbäck
Micromanagement is a very important aspect of real-time strategy (RTS) games. It involves moving single units or groups of units effectively on the battle field, targeting the most threatening enemy units and use the unit's special abilities when they are the most harmful for the enemy or the most beneficial for the player. Designing good micromanagement is a challenging task for AI bot developers. In this paper, we address the micromanagement subtask of positioning units effectively in combat situations. Two different approaches are evaluated, one based on potential fields and the other based on flocking algorithms. The results show that both the potential fields version and the flocking version clearly increases the win percentage of the bot, but the difference in wins between the two is minimal. The results also show that the more flexible potential fields technique requires much more hardware resources than the more simple flocking technique.
{"title":"Hybrid Pathfinding in StarCraft","authors":"Johan Hagelbäck","doi":"10.1109/TCIAIG.2015.2414447","DOIUrl":"https://doi.org/10.1109/TCIAIG.2015.2414447","url":null,"abstract":"Micromanagement is a very important aspect of real-time strategy (RTS) games. It involves moving single units or groups of units effectively on the battle field, targeting the most threatening enemy units and use the unit's special abilities when they are the most harmful for the enemy or the most beneficial for the player. Designing good micromanagement is a challenging task for AI bot developers. In this paper, we address the micromanagement subtask of positioning units effectively in combat situations. Two different approaches are evaluated, one based on potential fields and the other based on flocking algorithms. The results show that both the potential fields version and the flocking version clearly increases the win percentage of the bot, but the difference in wins between the two is minimal. The results also show that the more flexible potential fields technique requires much more hardware resources than the more simple flocking technique.","PeriodicalId":49192,"journal":{"name":"IEEE Transactions on Computational Intelligence and AI in Games","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/TCIAIG.2015.2414447","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"62592954","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}
Pub Date : 2016-12-01DOI: 10.1109/TCIAIG.2015.2490279
Marco Lippi
In this paper, we motivate the use of models and algorithms from the area of Statistical Relational Learning (SRL) as a framework for the description and the analysis of games. SRL combines the powerful formalism of first-order logic with the capability of probabilistic graphical models in handling uncertainty in data and representing dependencies between random variables: for this reason, SRL models can be effectively used to represent several categories of games, including games with partial information, graphical games and stochastic games. Inference algorithms can be used to approach the opponent modeling problem, as well as to find Nash equilibria or Pareto optimal solutions. Structure learning algorithms can be applied, in order to automatically extract probabilistic logic clauses describing the strategies of an opponent with a high-level, human-interpretable formalism. Experiments conducted using Markov logic networks, one of the most used SRL frameworks, show the potential of the approach.
{"title":"Statistical Relational Learning for Game Theory","authors":"Marco Lippi","doi":"10.1109/TCIAIG.2015.2490279","DOIUrl":"https://doi.org/10.1109/TCIAIG.2015.2490279","url":null,"abstract":"In this paper, we motivate the use of models and algorithms from the area of Statistical Relational Learning (SRL) as a framework for the description and the analysis of games. SRL combines the powerful formalism of first-order logic with the capability of probabilistic graphical models in handling uncertainty in data and representing dependencies between random variables: for this reason, SRL models can be effectively used to represent several categories of games, including games with partial information, graphical games and stochastic games. Inference algorithms can be used to approach the opponent modeling problem, as well as to find Nash equilibria or Pareto optimal solutions. Structure learning algorithms can be applied, in order to automatically extract probabilistic logic clauses describing the strategies of an opponent with a high-level, human-interpretable formalism. Experiments conducted using Markov logic networks, one of the most used SRL frameworks, show the potential of the approach.","PeriodicalId":49192,"journal":{"name":"IEEE Transactions on Computational Intelligence and AI in Games","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/TCIAIG.2015.2490279","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"62593017","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}
Pub Date : 2016-12-01DOI: 10.1109/TCIAIG.2015.2487743
Gabriel Synnaeve, P. Bessière
This paper showcases the use of Bayesian models for real-time strategy (RTS) games AI in three distinct core components: micromanagement (units control), tactics (army moves and positions), and strategy (economy, technology, production, army types). The strength of having end-to-end probabilistic models is that distributions on specific variables can be used to interconnect different models at different levels of abstraction. We applied this modeling to StarCraft, and evaluated each model independently. Along the way, we produced and released a comprehensive data set for RTS machine learning.
{"title":"Multiscale Bayesian Modeling for RTS Games: An Application to StarCraft AI","authors":"Gabriel Synnaeve, P. Bessière","doi":"10.1109/TCIAIG.2015.2487743","DOIUrl":"https://doi.org/10.1109/TCIAIG.2015.2487743","url":null,"abstract":"This paper showcases the use of Bayesian models for real-time strategy (RTS) games AI in three distinct core components: micromanagement (units control), tactics (army moves and positions), and strategy (economy, technology, production, army types). The strength of having end-to-end probabilistic models is that distributions on specific variables can be used to interconnect different models at different levels of abstraction. We applied this modeling to StarCraft, and evaluated each model independently. Along the way, we produced and released a comprehensive data set for RTS machine learning.","PeriodicalId":49192,"journal":{"name":"IEEE Transactions on Computational Intelligence and AI in Games","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/TCIAIG.2015.2487743","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"62593369","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}
Pub Date : 2016-09-01DOI: 10.1109/TCIAIG.2015.2420191
G. Gévay, Gábor Danner
The strong solutions of Nine Men's Morris and its variant, Lasker Morris, are well-known results (the starting positions are draws). We reexamined both of these games, and calculated extended strong solutions for them. By this, we mean the game-theoretic values of all possible game states that could be reached from certain starting positions where the number of stones to be placed by the players is different from the standard rules. These were also calculated for a previously unsolved third variant, Morabaraba, with interesting results: most of the starting positions where the players can place an equal number of stones (including the standard starting position) are wins for the first player (as opposed to the above games, where these are usually draws). We also developed a multivalued retrograde analysis, and used it as a basis for an algorithm for solving these games ultra-strongly. This means that when our program is playing against a fallible opponent, it has a greater chance of achieving a better result than the game-theoretic value, compared to randomly selecting between “just strongly” optimal moves. Previous attempts on ultrastrong solutions used local heuristics or learning during games, but we incorporated our algorithm into the retrograde analysis.
{"title":"Calculating Ultrastrong and Extended Solutions for Nine Men’s Morris, Morabaraba, and Lasker Morris","authors":"G. Gévay, Gábor Danner","doi":"10.1109/TCIAIG.2015.2420191","DOIUrl":"https://doi.org/10.1109/TCIAIG.2015.2420191","url":null,"abstract":"The strong solutions of Nine Men's Morris and its variant, Lasker Morris, are well-known results (the starting positions are draws). We reexamined both of these games, and calculated extended strong solutions for them. By this, we mean the game-theoretic values of all possible game states that could be reached from certain starting positions where the number of stones to be placed by the players is different from the standard rules. These were also calculated for a previously unsolved third variant, Morabaraba, with interesting results: most of the starting positions where the players can place an equal number of stones (including the standard starting position) are wins for the first player (as opposed to the above games, where these are usually draws). We also developed a multivalued retrograde analysis, and used it as a basis for an algorithm for solving these games ultra-strongly. This means that when our program is playing against a fallible opponent, it has a greater chance of achieving a better result than the game-theoretic value, compared to randomly selecting between “just strongly” optimal moves. Previous attempts on ultrastrong solutions used local heuristics or learning during games, but we incorporated our algorithm into the retrograde analysis.","PeriodicalId":49192,"journal":{"name":"IEEE Transactions on Computational Intelligence and AI in Games","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/TCIAIG.2015.2420191","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"62592567","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}
Pub Date : 2016-09-01DOI: 10.1109/TCIAIG.2015.2421493
Jason M. Traish, J. Tulip, W. Moore
Cache-based path-finding algorithms lose much of their advantage in dynamic environments where fast online search algorithms are required. Jump point search (JPS) is such a fast algorithm. It works by eliminating most map nodes from evaluation during path expansion. Boundary lookup jump point search (BL-JPS) is a modification that improves the speed of JPS. BL-JPS records the positions of obstacle boundaries and uses these via direct lookup to eliminate much of the iteration involved in searching for jump points in the JPS algorithm. Two sets of experiments are presented, demonstrating the effects of BL-JPS in both static and dynamic environments. The effects of different approaches to cache rebuilding for JPS+ in dynamic environments are also evaluated. Results show that BL-JPS is generally much faster than JPS. It is slower than JPS+ in static environments, but in dynamic environments, BL-JPS outperforms JPS+ for a single search. When multiple paths are searched, the effects of cache rebuilding gradually dominate the effects of search speed, resulting in JPS+ again becoming faster. However, combining JPS+ with BL-JPS provides a very fast path-finding algorithm (BL-JPS+) that outperforms JPS+ over a range of map types and numbers of paths searched.
{"title":"Optimization Using Boundary Lookup Jump Point Search","authors":"Jason M. Traish, J. Tulip, W. Moore","doi":"10.1109/TCIAIG.2015.2421493","DOIUrl":"https://doi.org/10.1109/TCIAIG.2015.2421493","url":null,"abstract":"Cache-based path-finding algorithms lose much of their advantage in dynamic environments where fast online search algorithms are required. Jump point search (JPS) is such a fast algorithm. It works by eliminating most map nodes from evaluation during path expansion. Boundary lookup jump point search (BL-JPS) is a modification that improves the speed of JPS. BL-JPS records the positions of obstacle boundaries and uses these via direct lookup to eliminate much of the iteration involved in searching for jump points in the JPS algorithm. Two sets of experiments are presented, demonstrating the effects of BL-JPS in both static and dynamic environments. The effects of different approaches to cache rebuilding for JPS+ in dynamic environments are also evaluated. Results show that BL-JPS is generally much faster than JPS. It is slower than JPS+ in static environments, but in dynamic environments, BL-JPS outperforms JPS+ for a single search. When multiple paths are searched, the effects of cache rebuilding gradually dominate the effects of search speed, resulting in JPS+ again becoming faster. However, combining JPS+ with BL-JPS provides a very fast path-finding algorithm (BL-JPS+) that outperforms JPS+ over a range of map types and numbers of paths searched.","PeriodicalId":49192,"journal":{"name":"IEEE Transactions on Computational Intelligence and AI in Games","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/TCIAIG.2015.2421493","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"62592643","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}
Pub Date : 2016-09-01DOI: 10.1109/TCIAIG.2015.2402393
Diego Perez Liebana, Spyridon Samothrakis, J. Togelius, T. Schaul, S. Lucas, Adrien Couëtoux, Jerry Lee, Chong-U Lim, Tommy Thompson
This paper presents the framework, rules, games, controllers, and results of the first General Video Game Playing Competition, held at the IEEE Conference on Computational Intelligence and Games in 2014. The competition proposes the challenge of creating controllers for general video game play, where a single agent must be able to play many different games, some of them unknown to the participants at the time of submitting their entries. This test can be seen as an approximation of general artificial intelligence, as the amount of game-dependent heuristics needs to be severely limited. The games employed are stochastic real-time scenarios (where the time budget to provide the next action is measured in milliseconds) with different winning conditions, scoring mechanisms, sprite types, and available actions for the player. It is a responsibility of the agents to discover the mechanics of each game, the requirements to obtain a high score and the requisites to finally achieve victory. This paper describes all controllers submitted to the competition, with an in-depth description of four of them by their authors, including the winner and the runner-up entries of the contest. The paper also analyzes the performance of the different approaches submitted, and finally proposes future tracks for the competition.
{"title":"The 2014 General Video Game Playing Competition","authors":"Diego Perez Liebana, Spyridon Samothrakis, J. Togelius, T. Schaul, S. Lucas, Adrien Couëtoux, Jerry Lee, Chong-U Lim, Tommy Thompson","doi":"10.1109/TCIAIG.2015.2402393","DOIUrl":"https://doi.org/10.1109/TCIAIG.2015.2402393","url":null,"abstract":"This paper presents the framework, rules, games, controllers, and results of the first General Video Game Playing Competition, held at the IEEE Conference on Computational Intelligence and Games in 2014. The competition proposes the challenge of creating controllers for general video game play, where a single agent must be able to play many different games, some of them unknown to the participants at the time of submitting their entries. This test can be seen as an approximation of general artificial intelligence, as the amount of game-dependent heuristics needs to be severely limited. The games employed are stochastic real-time scenarios (where the time budget to provide the next action is measured in milliseconds) with different winning conditions, scoring mechanisms, sprite types, and available actions for the player. It is a responsibility of the agents to discover the mechanics of each game, the requirements to obtain a high score and the requisites to finally achieve victory. This paper describes all controllers submitted to the competition, with an in-depth description of four of them by their authors, including the winner and the runner-up entries of the contest. The paper also analyzes the performance of the different approaches submitted, and finally proposes future tracks for the competition.","PeriodicalId":49192,"journal":{"name":"IEEE Transactions on Computational Intelligence and AI in Games","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/TCIAIG.2015.2402393","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"62592846","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}
Pub Date : 2016-09-01DOI: 10.1109/TCIAIG.2015.2425795
F. Liberatore, A. García, P. Castillo, J. J. M. Guervós
In the last year, thanks to the Ms. Pac-Man Versus Ghosts Competition, the game of Ms. Pac-Man has gained increasing attention from academics in the field of computational intelligence. In this paper, we contribute to this research stream by presenting a simple genetic algorithm with lexicographic ranking (GALR) for the optimization of flocking strategy-based ghost controllers. Flocking strategies are a paradigm for intelligent agents characterized by showing emergent behavior and for having very little computational and memory requirements, making them well suited for commercial applications and mobile devices. In particular, we study empirically the effect of optimizing homogeneous and heterogeneous teams. The computational analysis shows that the flocking strategy-based controllers generated by the proposed GALR outperform the ghost controllers included in the competition framework and some of those presented in the literature.
{"title":"Comparing Heterogeneous and Homogeneous Flocking Strategies for the Ghost Team in the Game of Ms. Pac-Man","authors":"F. Liberatore, A. García, P. Castillo, J. J. M. Guervós","doi":"10.1109/TCIAIG.2015.2425795","DOIUrl":"https://doi.org/10.1109/TCIAIG.2015.2425795","url":null,"abstract":"In the last year, thanks to the Ms. Pac-Man Versus Ghosts Competition, the game of Ms. Pac-Man has gained increasing attention from academics in the field of computational intelligence. In this paper, we contribute to this research stream by presenting a simple genetic algorithm with lexicographic ranking (GALR) for the optimization of flocking strategy-based ghost controllers. Flocking strategies are a paradigm for intelligent agents characterized by showing emergent behavior and for having very little computational and memory requirements, making them well suited for commercial applications and mobile devices. In particular, we study empirically the effect of optimizing homogeneous and heterogeneous teams. The computational analysis shows that the flocking strategy-based controllers generated by the proposed GALR outperform the ghost controllers included in the competition framework and some of those presented in the literature.","PeriodicalId":49192,"journal":{"name":"IEEE Transactions on Computational Intelligence and AI in Games","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/TCIAIG.2015.2425795","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"62593048","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：