General game playing, a relatively new field in game research, presents new frontiers in building intelligent game players. The traditional premise for building a good artificially intelligent player is that the game is known to the player and pre-programmed to play accordingly. General game players challenge game programmers by not identifying the game until the beginning of game play. In this paper we explore a new approach to intelligent general game playing employing a self-organizing, multiple-agent evolutionary learning strategy. In order to decide on an intelligent move, specialized agents interact with each other and evolve competitive solutions to decide on the best move, sharing the learnt experience and using it to train themselves in a social environment. In an experimental setup using a simple board game, the evolutionary agents employing a learning strategy by training themselves from their own experiences, and without prior knowledge of the game, demonstrate to be as effective as other strong dedicated heuristics. This approach provides a potential for new intelligent game playing program design in the absence of prior knowledge of the game at hand
{"title":"A Multi-Agent Architecture for Game Playing","authors":"Ziad Kobti, Shiven Sharma","doi":"10.1109/CIG.2007.368109","DOIUrl":"https://doi.org/10.1109/CIG.2007.368109","url":null,"abstract":"General game playing, a relatively new field in game research, presents new frontiers in building intelligent game players. The traditional premise for building a good artificially intelligent player is that the game is known to the player and pre-programmed to play accordingly. General game players challenge game programmers by not identifying the game until the beginning of game play. In this paper we explore a new approach to intelligent general game playing employing a self-organizing, multiple-agent evolutionary learning strategy. In order to decide on an intelligent move, specialized agents interact with each other and evolve competitive solutions to decide on the best move, sharing the learnt experience and using it to train themselves in a social environment. In an experimental setup using a simple board game, the evolutionary agents employing a learning strategy by training themselves from their own experiences, and without prior knowledge of the game, demonstrate to be as effective as other strong dedicated heuristics. This approach provides a potential for new intelligent game playing program design in the absence of prior knowledge of the game at hand","PeriodicalId":365269,"journal":{"name":"2007 IEEE Symposium on Computational Intelligence and Games","volume":"30 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":"125151264","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}
Adversarial planning in highly complex decision domains, such as modern video games, has not yet received much attention from AI researchers. In this paper, we present a planning framework that uses strategy simulation in conjunction with Nash-equilibrium strategy approximation. We apply this framework to an army deployment problem in a real-time strategy game setting and present experimental results that indicate a performance gain over the scripted strategies that the system is built on. This technique provides an automated way of increasing the decision quality of scripted AI systems and is therefore ideally suited for video games and combat simulators
{"title":"Adversarial Planning Through Strategy Simulation","authors":"Franisek Sailer, M. Buro, Marc Lanctot","doi":"10.1109/CIG.2007.368082","DOIUrl":"https://doi.org/10.1109/CIG.2007.368082","url":null,"abstract":"Adversarial planning in highly complex decision domains, such as modern video games, has not yet received much attention from AI researchers. In this paper, we present a planning framework that uses strategy simulation in conjunction with Nash-equilibrium strategy approximation. We apply this framework to an army deployment problem in a real-time strategy game setting and present experimental results that indicate a performance gain over the scripted strategies that the system is built on. This technique provides an automated way of increasing the decision quality of scripted AI systems and is therefore ideally suited for video games and combat simulators","PeriodicalId":365269,"journal":{"name":"2007 IEEE Symposium on Computational Intelligence and Games","volume":"20 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":"132280452","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}
Although a number of multi-objective evolutionary algorithms (MOEAs) have been proposed over the last two decades, very few studies have utilized MOEAs for game agent synthesis. Recently, we have suggested a co-evolutionary implementation using the Pareto evolutionary programming (PEP) algorithm. This paper describes a series of experiments using PEP for evolving artificial neural networks (ANNs) that act as game-playing agents. Three systems are compared: (i) a canonical PEP system, (ii) a co-evolving PEP system (PCEP) with 3 different setups, and (iii) a co-evolving PEP system that uses an archive (PCEP-A) with 3 different setups. The aim of this study is to provide insights on the effects of including co-evolutionary techniques on a MOEA by investigating and comparing these 3 different approaches in evolving intelligent agents as both first and second players in a deterministic zero-sum board game. The results indicate that the canonical PEP system outperformed both co-evolutionary PEP systems as it was able to evolve ANN agents with higher quality game-playing performance as both first and second game players. Hence, this study shows that a canonical MOEA without co-evolution is desirable for the synthesis of cognitive game AI agents
{"title":"Pareto Evolution and Co-Evolution in Cognitive Neural Agents Synthesis for Tic-Tac-Toe","authors":"Y. J. Yau, J. Teo, P. Anthony","doi":"10.1109/CIG.2007.368113","DOIUrl":"https://doi.org/10.1109/CIG.2007.368113","url":null,"abstract":"Although a number of multi-objective evolutionary algorithms (MOEAs) have been proposed over the last two decades, very few studies have utilized MOEAs for game agent synthesis. Recently, we have suggested a co-evolutionary implementation using the Pareto evolutionary programming (PEP) algorithm. This paper describes a series of experiments using PEP for evolving artificial neural networks (ANNs) that act as game-playing agents. Three systems are compared: (i) a canonical PEP system, (ii) a co-evolving PEP system (PCEP) with 3 different setups, and (iii) a co-evolving PEP system that uses an archive (PCEP-A) with 3 different setups. The aim of this study is to provide insights on the effects of including co-evolutionary techniques on a MOEA by investigating and comparing these 3 different approaches in evolving intelligent agents as both first and second players in a deterministic zero-sum board game. The results indicate that the canonical PEP system outperformed both co-evolutionary PEP systems as it was able to evolve ANN agents with higher quality game-playing performance as both first and second game players. Hence, this study shows that a canonical MOEA without co-evolution is desirable for the synthesis of cognitive game AI agents","PeriodicalId":365269,"journal":{"name":"2007 IEEE Symposium on Computational Intelligence and Games","volume":"6 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":"132771329","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}
Many games require opponent modeling for optimal performance. The implicit learning and adaptive nature of evolutionary computation techniques offer a natural way to develop and explore models of an opponent's strategy without significant overhead. In this paper, we compare two learning techniques for strategy development in the game of Spoof, a simple guessing game of imperfect information. We compare a genetic programming approach with a look-up table based approach, contrasting the performance of each in different scenarios of the game. Results show both approaches have their advantages, but that the genetic programming approach achieves better performance in scenarios with little public information. We also trial both approaches against opponents who vary their strategy; results showing that the genetic programming approach is better able to respond to strategy changes than the look-up table based approach
{"title":"A Comparison of Genetic Programming and Look-up Table Learning for the Game of Spoof","authors":"M. Wittkamp, L. Barone, Lyndon While","doi":"10.1109/CIG.2007.368080","DOIUrl":"https://doi.org/10.1109/CIG.2007.368080","url":null,"abstract":"Many games require opponent modeling for optimal performance. The implicit learning and adaptive nature of evolutionary computation techniques offer a natural way to develop and explore models of an opponent's strategy without significant overhead. In this paper, we compare two learning techniques for strategy development in the game of Spoof, a simple guessing game of imperfect information. We compare a genetic programming approach with a look-up table based approach, contrasting the performance of each in different scenarios of the game. Results show both approaches have their advantages, but that the genetic programming approach achieves better performance in scenarios with little public information. We also trial both approaches against opponents who vary their strategy; results showing that the genetic programming approach is better able to respond to strategy changes than the look-up table based approach","PeriodicalId":365269,"journal":{"name":"2007 IEEE Symposium on Computational Intelligence and Games","volume":"74 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":"127867521","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}
Learning controllers for the space combat game Xpilot is a difficult problem. Using evolutionary computation to evolve the weights for a neural network could create an effective/adaptive controller that does not require extensive programmer input. Previous attempts have been successful in that the controlled agents were transformed from aimless wanderers into interactive agents, but these methods have not resulted in controllers that are competitive with those learned using other methods. In this paper, we present a neural network learning method that uses a genetic algorithm to select the network inputs and node thresholds, along with connection weights, to evolve competitive Xpilot agents
{"title":"The Evolution of Multi-Layer Neural Networks for the Control of Xpilot Agents","authors":"M. Parker, G. Parker","doi":"10.1109/CIG.2007.368103","DOIUrl":"https://doi.org/10.1109/CIG.2007.368103","url":null,"abstract":"Learning controllers for the space combat game Xpilot is a difficult problem. Using evolutionary computation to evolve the weights for a neural network could create an effective/adaptive controller that does not require extensive programmer input. Previous attempts have been successful in that the controlled agents were transformed from aimless wanderers into interactive agents, but these methods have not resulted in controllers that are competitive with those learned using other methods. In this paper, we present a neural network learning method that uses a genetic algorithm to select the network inputs and node thresholds, along with connection weights, to evolve competitive Xpilot agents","PeriodicalId":365269,"journal":{"name":"2007 IEEE Symposium on Computational Intelligence and Games","volume":"27 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":"115501382","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}
Multiplayer games with imperfect information, such as Bridge, are especially challenging for game theory researchers. Although several algorithmic techniques have been successfully applied to the card play phase of the game, bidding requires a much different approach. We have shown that a special form of a neural network, called a self-organizing map (SOM), can be used to effectively bid no trump hands. The characteristic boundary that forms between resulting neighboring nodes in a SOM is an ideal mechanism for modeling the imprecise and ambiguous nature of the game
{"title":"Bridge Bidding with Imperfect Information","authors":"L. DeLooze, J. Downey","doi":"10.1109/CIG.2007.368122","DOIUrl":"https://doi.org/10.1109/CIG.2007.368122","url":null,"abstract":"Multiplayer games with imperfect information, such as Bridge, are especially challenging for game theory researchers. Although several algorithmic techniques have been successfully applied to the card play phase of the game, bidding requires a much different approach. We have shown that a special form of a neural network, called a self-organizing map (SOM), can be used to effectively bid no trump hands. The characteristic boundary that forms between resulting neighboring nodes in a SOM is an ideal mechanism for modeling the imprecise and ambiguous nature of the game","PeriodicalId":365269,"journal":{"name":"2007 IEEE Symposium on Computational Intelligence and Games","volume":"7 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":"124130074","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 this paper we use computational techniques to explore the Aztec board game of Patolli. Rules for the game were documented by the Spanish explorers that ultimately destroyed the Aztec civilization, yet there is no guarantee that the few players of Patolli that still exist follow the same strategies as the Aztec originators of the game. We implemented the rules of the game in an agent-based system and designed a series of experiments to pit game-playing agents using different strategies against each other to try to infer what makes a good strategy (and therefore what kind of information would have been taken into account by expert Aztec players back in the days when Patolli was an extremely popular game). In this paper we describe the game, explain our implementation, and present our experimental setup, results and conclusions.
{"title":"Inferring the Past: A Computational Exploration of the Strategies that May Have Been Used in the Aztec Board Game of Patolli","authors":"A. Garza, C. Flores","doi":"10.1109/CIG.2007.368112","DOIUrl":"https://doi.org/10.1109/CIG.2007.368112","url":null,"abstract":"In this paper we use computational techniques to explore the Aztec board game of Patolli. Rules for the game were documented by the Spanish explorers that ultimately destroyed the Aztec civilization, yet there is no guarantee that the few players of Patolli that still exist follow the same strategies as the Aztec originators of the game. We implemented the rules of the game in an agent-based system and designed a series of experiments to pit game-playing agents using different strategies against each other to try to infer what makes a good strategy (and therefore what kind of information would have been taken into account by expert Aztec players back in the days when Patolli was an extremely popular game). In this paper we describe the game, explain our implementation, and present our experimental setup, results and conclusions.","PeriodicalId":365269,"journal":{"name":"2007 IEEE Symposium on Computational Intelligence and Games","volume":"51 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":"132069380","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}
M. Greenspan, Joseph Lam, W. Leckie, Marc Godard, Imran Zaidi, Ken Anderson, Donna C. Dupuis, Sam Jordan
This paper describes the development of Deep Green, an intelligent robotic system that is currently in development to play competitive pool against a proficient human opponent. The design philosophy and the main system components are presented, and the progress to date is summarized. We also address a common misconception about the game of pool, i.e. that it is purely a game of physical skill, requiring little or no intelligence or strategy. We explain some of the difficulties in developing a vision-based system with a high degree of positional accuracy. We further demonstrate that even if perfect accuracy were possible, it is still beneficial and necessary to play strategically.
{"title":"Toward a Competitive Pool Playing Robot: Is Computational Intelligence Needed to Play Robotic Pool?","authors":"M. Greenspan, Joseph Lam, W. Leckie, Marc Godard, Imran Zaidi, Ken Anderson, Donna C. Dupuis, Sam Jordan","doi":"10.1109/CIG.2007.368124","DOIUrl":"https://doi.org/10.1109/CIG.2007.368124","url":null,"abstract":"This paper describes the development of Deep Green, an intelligent robotic system that is currently in development to play competitive pool against a proficient human opponent. The design philosophy and the main system components are presented, and the progress to date is summarized. We also address a common misconception about the game of pool, i.e. that it is purely a game of physical skill, requiring little or no intelligence or strategy. We explain some of the difficulties in developing a vision-based system with a high degree of positional accuracy. We further demonstrate that even if perfect accuracy were possible, it is still beneficial and necessary to play strategically.","PeriodicalId":365269,"journal":{"name":"2007 IEEE Symposium on Computational Intelligence and Games","volume":"111 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":"115254355","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 synchronized games the players make their moves simultaneously and, as a consequence, the concept of turn does not exist. Synchronized Cutcake is the synchronized version of Cutcake, a classical two-player combinatorial game. Even though to determine the solution of Cutcake is trivial, solving Synchronized Cutcake is challenging because of the calculation of the game's value. We present the solution for small board size and some general results for a board of arbitrary size
{"title":"The Game of Synchronized Cutcake","authors":"A. Cincotti, H. Iida","doi":"10.1109/CIG.2007.368123","DOIUrl":"https://doi.org/10.1109/CIG.2007.368123","url":null,"abstract":"In synchronized games the players make their moves simultaneously and, as a consequence, the concept of turn does not exist. Synchronized Cutcake is the synchronized version of Cutcake, a classical two-player combinatorial game. Even though to determine the solution of Cutcake is trivial, solving Synchronized Cutcake is challenging because of the calculation of the game's value. We present the solution for small board size and some general results for a board of arbitrary size","PeriodicalId":365269,"journal":{"name":"2007 IEEE Symposium on Computational Intelligence and Games","volume":"50 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":"123839001","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}
We use a genetic algorithm to explore the space of pathfinding algorithms in Lagoon, a 3D naval real-time strategy game and training simulation. To aid in training, Lagoon tries to provide a rich environment with many agents (boats) that maneuver realistically. A*, the traditional pathfinding algorithm in games is computationally expensive when run for many agents and A* paths quickly lose validity as agents move. Although there is a large literature targeted at making A* implementations faster, we want believability and optimal paths may not be believable. In this paper we use a genetic algorithm to search the space of network search algorithms like A* to find new pathfinding algorithms that are near-optimal, fast, and believable. Our results indicate that the genetic algorithm can explore this space well and that novel pathfinding algorithms (found by our genetic algorithm) quickly find near-optimal, more-believable paths in Lagoon
{"title":"Using a Genetic Algorithm to Explore A*-like Pathfinding Algorithms","authors":"Ryan E. Leigh, S. Louis, C. Miles","doi":"10.1109/CIG.2007.368081","DOIUrl":"https://doi.org/10.1109/CIG.2007.368081","url":null,"abstract":"We use a genetic algorithm to explore the space of pathfinding algorithms in Lagoon, a 3D naval real-time strategy game and training simulation. To aid in training, Lagoon tries to provide a rich environment with many agents (boats) that maneuver realistically. A*, the traditional pathfinding algorithm in games is computationally expensive when run for many agents and A* paths quickly lose validity as agents move. Although there is a large literature targeted at making A* implementations faster, we want believability and optimal paths may not be believable. In this paper we use a genetic algorithm to search the space of network search algorithms like A* to find new pathfinding algorithms that are near-optimal, fast, and believable. Our results indicate that the genetic algorithm can explore this space well and that novel pathfinding algorithms (found by our genetic algorithm) quickly find near-optimal, more-believable paths in Lagoon","PeriodicalId":365269,"journal":{"name":"2007 IEEE Symposium on Computational Intelligence and Games","volume":"135 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":"115838950","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：