Pub Date : 2015-12-01DOI: 10.1109/TCIAIG.2014.2345842
Diego Perez Liebana, Sanaz Mostaghim, Spyridon Samothrakis, S. Lucas
Multiobjective optimization has been traditionally a matter of study in domains like engineering or finance, with little impact on games research. However, action-decision based on multiobjective evaluation may be beneficial in order to obtain a high quality level of play. This paper presents a multiobjective Monte Carlo tree search algorithm for planning and control in real-time game domains, those where the time budget to decide the next move to make is close to 40 ms. A comparison is made between the proposed algorithm, a single-objective version of Monte Carlo tree search and a rolling horizon implementation of nondominated sorting evolutionary algorithm II (NSGA-II). Two different benchmarks are employed, deep sea treasure (DST) and the multiobjective physical traveling salesman problem (MO-PTSP). Using the same heuristics on each game, the analysis is focused on how well the algorithms explore the search space. Results show that the algorithm proposed outperforms NSGA-II. Additionally, it is also shown that the algorithm is able to converge to different optimal solutions or the optimal Pareto front (if achieved during search).
{"title":"Multiobjective Monte Carlo Tree Search for Real-Time Games","authors":"Diego Perez Liebana, Sanaz Mostaghim, Spyridon Samothrakis, S. Lucas","doi":"10.1109/TCIAIG.2014.2345842","DOIUrl":"https://doi.org/10.1109/TCIAIG.2014.2345842","url":null,"abstract":"Multiobjective optimization has been traditionally a matter of study in domains like engineering or finance, with little impact on games research. However, action-decision based on multiobjective evaluation may be beneficial in order to obtain a high quality level of play. This paper presents a multiobjective Monte Carlo tree search algorithm for planning and control in real-time game domains, those where the time budget to decide the next move to make is close to 40 ms. A comparison is made between the proposed algorithm, a single-objective version of Monte Carlo tree search and a rolling horizon implementation of nondominated sorting evolutionary algorithm II (NSGA-II). Two different benchmarks are employed, deep sea treasure (DST) and the multiobjective physical traveling salesman problem (MO-PTSP). Using the same heuristics on each game, the analysis is focused on how well the algorithms explore the search space. Results show that the algorithm proposed outperforms NSGA-II. Additionally, it is also shown that the algorithm is able to converge to different optimal solutions or the optimal Pareto front (if achieved during search).","PeriodicalId":49192,"journal":{"name":"IEEE Transactions on Computational Intelligence and AI in Games","volume":"7 1","pages":"347-360"},"PeriodicalIF":0.0,"publicationDate":"2015-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/TCIAIG.2014.2345842","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"62592381","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 : 2015-12-01DOI: 10.1109/TCIAIG.2014.2346690
A. Ramirez, V. Bulitko
Storytelling plays an important role in human life, from everyday communication to entertainment. Interactive storytelling (IS) offers its audience an opportunity to actively participate in the story being told, particularly in video games. Managing the narrative experience of the player is a complex process that involves choices, authorial goals and constraints of a given story setting (e.g., a fairy tale). Over the last several decades, a number of experience managers using artificial intelligence (AI) methods such as planning and constraint satisfaction have been developed. In this paper, we extend existing work and propose a new AI experience manager called player-specific automated storytelling (PAST), which uses automated planning to satisfy the story setting and authorial constraints in response to the player's actions. Out of the possible stories algorithmically generated by the planner in response, the one that is expected to suit the player's style best is selected. To do so, we employ automated player modeling. We evaluate PAST within a video-game domain with user studies and discuss the effects of combining planning and player modeling on the player's perception of agency.
{"title":"Automated Planning and Player Modeling for Interactive Storytelling","authors":"A. Ramirez, V. Bulitko","doi":"10.1109/TCIAIG.2014.2346690","DOIUrl":"https://doi.org/10.1109/TCIAIG.2014.2346690","url":null,"abstract":"Storytelling plays an important role in human life, from everyday communication to entertainment. Interactive storytelling (IS) offers its audience an opportunity to actively participate in the story being told, particularly in video games. Managing the narrative experience of the player is a complex process that involves choices, authorial goals and constraints of a given story setting (e.g., a fairy tale). Over the last several decades, a number of experience managers using artificial intelligence (AI) methods such as planning and constraint satisfaction have been developed. In this paper, we extend existing work and propose a new AI experience manager called player-specific automated storytelling (PAST), which uses automated planning to satisfy the story setting and authorial constraints in response to the player's actions. Out of the possible stories algorithmically generated by the planner in response, the one that is expected to suit the player's style best is selected. To do so, we employ automated player modeling. We evaluate PAST within a video-game domain with user studies and discuss the effects of combining planning and player modeling on the player's perception of agency.","PeriodicalId":49192,"journal":{"name":"IEEE Transactions on Computational Intelligence and AI in Games","volume":"7 1","pages":"375-386"},"PeriodicalIF":0.0,"publicationDate":"2015-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/TCIAIG.2014.2346690","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"62592451","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 : 2015-12-01DOI: 10.1109/TCIAIG.2014.2339221
Georgios N. Yannakakis, J. Togelius
This paper attempts to give a high-level overview of the field of artificial and computational intelligence (AI/CI) in games, with particular reference to how the different core research areas within this field inform and interact with each other, both actually and potentially. We identify ten main research areas within this field: NPC behavior learning, search and planning, player modeling, games as AI benchmarks, procedural content generation, computational narrative, believable agents, AI-assisted game design, general game artificial intelligence and AI in commercial games. We view and analyze the areas from three key perspectives: 1) the dominant AI method(s) used under each area; 2) the relation of each area with respect to the end (human) user; and 3) the placement of each area within a human-computer (player-game) interaction perspective. In addition, for each of these areas we consider how it could inform or interact with each of the other areas; in those cases where we find that meaningful interaction either exists or is possible, we describe the character of that interaction and provide references to published studies, if any. We believe that this paper improves understanding of the current nature of the game AI/CI research field and the interdependences between its core areas by providing a unifying overview. We also believe that the discussion of potential interactions between research areas provides a pointer to many interesting future research projects and unexplored subfields.
{"title":"A Panorama of Artificial and Computational Intelligence in Games","authors":"Georgios N. Yannakakis, J. Togelius","doi":"10.1109/TCIAIG.2014.2339221","DOIUrl":"https://doi.org/10.1109/TCIAIG.2014.2339221","url":null,"abstract":"This paper attempts to give a high-level overview of the field of artificial and computational intelligence (AI/CI) in games, with particular reference to how the different core research areas within this field inform and interact with each other, both actually and potentially. We identify ten main research areas within this field: NPC behavior learning, search and planning, player modeling, games as AI benchmarks, procedural content generation, computational narrative, believable agents, AI-assisted game design, general game artificial intelligence and AI in commercial games. We view and analyze the areas from three key perspectives: 1) the dominant AI method(s) used under each area; 2) the relation of each area with respect to the end (human) user; and 3) the placement of each area within a human-computer (player-game) interaction perspective. In addition, for each of these areas we consider how it could inform or interact with each of the other areas; in those cases where we find that meaningful interaction either exists or is possible, we describe the character of that interaction and provide references to published studies, if any. We believe that this paper improves understanding of the current nature of the game AI/CI research field and the interdependences between its core areas by providing a unifying overview. We also believe that the discussion of potential interactions between research areas provides a pointer to many interesting future research projects and unexplored subfields.","PeriodicalId":49192,"journal":{"name":"IEEE Transactions on Computational Intelligence and AI in Games","volume":"7 1","pages":"317-335"},"PeriodicalIF":0.0,"publicationDate":"2015-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/TCIAIG.2014.2339221","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"62592255","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 : 2015-12-01DOI: 10.1109/TCIAIG.2014.2346997
L. Schaefers, M. Platzner
Monte Carlo tree search (MCTS) has brought about great success regarding the evaluation of stochastic and deterministic games in recent years. We present and empirically analyze a data-driven parallelization approach for MCTS targeting large HPC clusters with Infiniband interconnect. Our implementation is based on OpenMPI and makes extensive use of its RDMA based asynchronous tiny message communication capabilities for effectively overlapping communication and computation. We integrate our parallel MCTS approach termed UCT-Treesplit in our state-of-the-art Go engine Gomorra and measure its strengths and limitations in a real-world setting. Our extensive experiments show that we can scale up to 128 compute nodes and 2048 cores in self-play experiments and, furthermore, give promising directions for additional improvement. The generality of our parallelization approach advocates its use to significantly improve the search quality of a huge number of current MCTS applications.
{"title":"Distributed Monte Carlo Tree Search: A Novel Technique and its Application to Computer Go","authors":"L. Schaefers, M. Platzner","doi":"10.1109/TCIAIG.2014.2346997","DOIUrl":"https://doi.org/10.1109/TCIAIG.2014.2346997","url":null,"abstract":"Monte Carlo tree search (MCTS) has brought about great success regarding the evaluation of stochastic and deterministic games in recent years. We present and empirically analyze a data-driven parallelization approach for MCTS targeting large HPC clusters with Infiniband interconnect. Our implementation is based on OpenMPI and makes extensive use of its RDMA based asynchronous tiny message communication capabilities for effectively overlapping communication and computation. We integrate our parallel MCTS approach termed UCT-Treesplit in our state-of-the-art Go engine Gomorra and measure its strengths and limitations in a real-world setting. Our extensive experiments show that we can scale up to 128 compute nodes and 2048 cores in self-play experiments and, furthermore, give promising directions for additional improvement. The generality of our parallelization approach advocates its use to significantly improve the search quality of a huge number of current MCTS applications.","PeriodicalId":49192,"journal":{"name":"IEEE Transactions on Computational Intelligence and AI in Games","volume":"7 1","pages":"361-374"},"PeriodicalIF":0.0,"publicationDate":"2015-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/TCIAIG.2014.2346997","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"62592464","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 : 2015-09-01DOI: 10.1109/TCIAIG.2014.2332442
Christian Wirth, Johannes Furnkranz
Most of the research in the area of evaluation function learning is focused on self-play. However in many domains, like Chess, expert feedback is amply available in the form of annotated games. This feedback usually comes in the form of qualitative information because human annotators find it hard to determine precise utility values for game states. The goal of this work is to investigate inasmuch it is possible to leverage this qualitative feedback for learning an evaluation function for the game. To this end, we show how the game annotations can be translated into preference statements over moves and game states, which in turn can be used for learning a utility function that respects these preference constraints. We evaluate the resulting function by creating multiple heuristics based upon different sized subsets of the training data and compare them in a tournament scenario. The results showed that learning from game annotations is possible, but, on the other hand, our learned functions did not quite reach the performance of the original, manually tuned function of the Chess program. The reason for this failure seems to lie in the fact that human annotators only annotate “interesting” positions, so that it is hard to learn basic information, such as material advantage from game annotations alone.
{"title":"On Learning From Game Annotations","authors":"Christian Wirth, Johannes Furnkranz","doi":"10.1109/TCIAIG.2014.2332442","DOIUrl":"https://doi.org/10.1109/TCIAIG.2014.2332442","url":null,"abstract":"Most of the research in the area of evaluation function learning is focused on self-play. However in many domains, like Chess, expert feedback is amply available in the form of annotated games. This feedback usually comes in the form of qualitative information because human annotators find it hard to determine precise utility values for game states. The goal of this work is to investigate inasmuch it is possible to leverage this qualitative feedback for learning an evaluation function for the game. To this end, we show how the game annotations can be translated into preference statements over moves and game states, which in turn can be used for learning a utility function that respects these preference constraints. We evaluate the resulting function by creating multiple heuristics based upon different sized subsets of the training data and compare them in a tournament scenario. The results showed that learning from game annotations is possible, but, on the other hand, our learned functions did not quite reach the performance of the original, manually tuned function of the Chess program. The reason for this failure seems to lie in the fact that human annotators only annotate “interesting” positions, so that it is hard to learn basic information, such as material advantage from game annotations alone.","PeriodicalId":49192,"journal":{"name":"IEEE Transactions on Computational Intelligence and AI in Games","volume":"7 1","pages":"304-316"},"PeriodicalIF":0.0,"publicationDate":"2015-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/TCIAIG.2014.2332442","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"62592225","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 : 2015-09-01DOI: 10.1109/TCIAIG.2014.2382718
Raphaël Marczak, G. Schott, P. Hanna
This paper introduces a new variant of gameplay metrics that further develops a set of processes that expand user-centered game testing practices capable of quantifying user experiences. The key goal of the method presented here is to widen the appeal and application of game metrics within research relevant to, and representative of the wider field of game studies. In doing so, we acknowledge that the interests of this research community is often focused on player experience and performance with a broad range of off-the-shelf games that have already been released to the public. In order to be able to include any PC game system within research (or audiovideo stream, e.g., YouTube walkthroughs) our approach comprises of a postprocessing method for analyzing player performance. Through exploiting the audiovisual streams that are transmitted to the player, this approach processes content activated and generated during play and is therefore representative of individual player's encounters with specific games.
{"title":"Postprocessing Gameplay Metrics for Gameplay Performance Segmentation Based on Audiovisual Analysis","authors":"Raphaël Marczak, G. Schott, P. Hanna","doi":"10.1109/TCIAIG.2014.2382718","DOIUrl":"https://doi.org/10.1109/TCIAIG.2014.2382718","url":null,"abstract":"This paper introduces a new variant of gameplay metrics that further develops a set of processes that expand user-centered game testing practices capable of quantifying user experiences. The key goal of the method presented here is to widen the appeal and application of game metrics within research relevant to, and representative of the wider field of game studies. In doing so, we acknowledge that the interests of this research community is often focused on player experience and performance with a broad range of off-the-shelf games that have already been released to the public. In order to be able to include any PC game system within research (or audiovideo stream, e.g., YouTube walkthroughs) our approach comprises of a postprocessing method for analyzing player performance. Through exploiting the audiovisual streams that are transmitted to the player, this approach processes content activated and generated during play and is therefore representative of individual player's encounters with specific games.","PeriodicalId":49192,"journal":{"name":"IEEE Transactions on Computational Intelligence and AI in Games","volume":"7 1","pages":"279-291"},"PeriodicalIF":0.0,"publicationDate":"2015-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/TCIAIG.2014.2382718","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"62592483","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 : 2015-09-01DOI: 10.1109/TCIAIG.2015.2467166
C. Bauckhage, Anders Drachen, Christian Thurau
The articles in this special section ddress various flavors of the diverse field of game analytics. It covers topics ranging from player profiling, behavioral prediction, metrics extraction from gameplay recordings, behavioral analysis, retention analysis, and more.
{"title":"The Age of Analytics","authors":"C. Bauckhage, Anders Drachen, Christian Thurau","doi":"10.1109/TCIAIG.2015.2467166","DOIUrl":"https://doi.org/10.1109/TCIAIG.2015.2467166","url":null,"abstract":"The articles in this special section ddress various flavors of the diverse field of game analytics. It covers topics ranging from player profiling, behavioral prediction, metrics extraction from gameplay recordings, behavioral analysis, retention analysis, and more.","PeriodicalId":49192,"journal":{"name":"IEEE Transactions on Computational Intelligence and AI in Games","volume":"42 1","pages":"205-206"},"PeriodicalIF":0.0,"publicationDate":"2015-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82513343","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 : 2015-09-01DOI: 10.1109/TCIAIG.2014.2357174
P. Cowling, Sam Devlin, E. Powley, D. Whitehouse, Jeff Rollason
Tuning game difficulty prior to release requires careful consideration. Players can quickly lose interest in a game if it is too hard or too easy. Assessing how players will cope prior to release is often inaccurate. However, modern games can now collect sufficient data to perform large scale analysis post deployment and update the product based on these insights. AI Factory Spades is currently the top rated Spades game in the Google Play store. In collaboration with the developers, we have collected gameplay data from 27 592 games and statistics regarding wins/losses for 99 866 games using Google Analytics. Using the data collected, this study analyses the difficulty and behavior of an Information Set Monte Carlo Tree Search player we developed and deployed in the game previously. The methods of data collection and analysis presented in this study are generally applicable. The same workflow could be used to analyze the difficulty and typical player or opponent behavior in any game. Furthermore, addressing issues of difficulty or nonhuman-like opponents postdeployment can positively affect player retention.
{"title":"Player Preference and Style in a Leading Mobile Card Game","authors":"P. Cowling, Sam Devlin, E. Powley, D. Whitehouse, Jeff Rollason","doi":"10.1109/TCIAIG.2014.2357174","DOIUrl":"https://doi.org/10.1109/TCIAIG.2014.2357174","url":null,"abstract":"Tuning game difficulty prior to release requires careful consideration. Players can quickly lose interest in a game if it is too hard or too easy. Assessing how players will cope prior to release is often inaccurate. However, modern games can now collect sufficient data to perform large scale analysis post deployment and update the product based on these insights. AI Factory Spades is currently the top rated Spades game in the Google Play store. In collaboration with the developers, we have collected gameplay data from 27 592 games and statistics regarding wins/losses for 99 866 games using Google Analytics. Using the data collected, this study analyses the difficulty and behavior of an Information Set Monte Carlo Tree Search player we developed and deployed in the game previously. The methods of data collection and analysis presented in this study are generally applicable. The same workflow could be used to analyze the difficulty and typical player or opponent behavior in any game. Furthermore, addressing issues of difficulty or nonhuman-like opponents postdeployment can positively affect player retention.","PeriodicalId":49192,"journal":{"name":"IEEE Transactions on Computational Intelligence and AI in Games","volume":"7 1","pages":"233-242"},"PeriodicalIF":0.0,"publicationDate":"2015-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/TCIAIG.2014.2357174","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"62592535","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 : 2015-08-10DOI: 10.1109/TCIAIG.2015.2466240
Hao Wang, Hao-Tsung Yang, Chuen-Tsai Sun
Almost all current matchmaking systems for team competition games based on player skill ratings contain algorithms designed to create teams consisting of players at similar skill levels. However, these systems overlook the important factor of playing style. In this paper, we analyze how playing style affects enjoyment in team competition games, using a mix of Sternberg's thinking style theory and individual histories in the form of statistics from previous matches to categorize League of Legend (LoL) players. Data for approximately 64 000 matches involving 185 000 players were taken from the LoLBase website. Match enjoyment was considered low when games lasted for 26 min or less (the earliest possible surrender time). Results from statistical analyses indicate that players with certain playing styles were more likely to enhance both game enjoyment and team strength. We also used a neural network model to test the usefulness of playing style information in predicting match quality. It is our hope that these results will support the establishment of more efficient matchmaking systems.
{"title":"Thinking Style and Team Competition Game Performance and Enjoyment","authors":"Hao Wang, Hao-Tsung Yang, Chuen-Tsai Sun","doi":"10.1109/TCIAIG.2015.2466240","DOIUrl":"https://doi.org/10.1109/TCIAIG.2015.2466240","url":null,"abstract":"Almost all current matchmaking systems for team competition games based on player skill ratings contain algorithms designed to create teams consisting of players at similar skill levels. However, these systems overlook the important factor of playing style. In this paper, we analyze how playing style affects enjoyment in team competition games, using a mix of Sternberg's thinking style theory and individual histories in the form of statistics from previous matches to categorize League of Legend (LoL) players. Data for approximately 64 000 matches involving 185 000 players were taken from the LoLBase website. Match enjoyment was considered low when games lasted for 26 min or less (the earliest possible surrender time). Results from statistical analyses indicate that players with certain playing styles were more likely to enhance both game enjoyment and team strength. We also used a neural network model to test the usefulness of playing style information in predicting match quality. It is our hope that these results will support the establishment of more efficient matchmaking systems.","PeriodicalId":49192,"journal":{"name":"IEEE Transactions on Computational Intelligence and AI in Games","volume":"7 1","pages":"243-254"},"PeriodicalIF":0.0,"publicationDate":"2015-08-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/TCIAIG.2015.2466240","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"62593276","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 : 2015-08-03DOI: 10.1109/TCIAIG.2016.2528499
Martin Černý, T. Plch, M. Marko, Jakub Gemrot, Petr Ondrácek, C. Brom
The quality of high-level AI of nonplayer characters (NPCs) in commercial open-world games (OWGs) has been increasing during the past years. However, due to constraints specific to the game industry, this increase has been slow and it has been driven by larger budgets rather than adoption of new complex AI techniques. Most of the contemporary AI is still expressed as hard-coded scripts. The complexity and manageability of the script codebase is one of the key limiting factors for further AI improvements. In this paper, we address this issue. We present behavior objects (BO)—a general approach to development of NPC behaviors for large OWGs. BOs are inspired by object-oriented programming and extend the concept of smart objects. Our approach promotes encapsulation of data and code for multiple related behaviors in one place, hiding internal details and embedding intelligence in the environment. BOs are a natural abstraction of five different techniques that we have implemented to manage AI complexity in an upcoming AAA OWG. We report the details of the implementations in the context of behavior trees and the lessons learned during development. Our study should serve as an inspiration for AI architecture designers from both the academia and the industry.
{"title":"Using Behavior Objects to Manage Complexity in Virtual Worlds","authors":"Martin Černý, T. Plch, M. Marko, Jakub Gemrot, Petr Ondrácek, C. Brom","doi":"10.1109/TCIAIG.2016.2528499","DOIUrl":"https://doi.org/10.1109/TCIAIG.2016.2528499","url":null,"abstract":"The quality of high-level AI of nonplayer characters (NPCs) in commercial open-world games (OWGs) has been increasing during the past years. However, due to constraints specific to the game industry, this increase has been slow and it has been driven by larger budgets rather than adoption of new complex AI techniques. Most of the contemporary AI is still expressed as hard-coded scripts. The complexity and manageability of the script codebase is one of the key limiting factors for further AI improvements. In this paper, we address this issue. We present behavior objects (BO)—a general approach to development of NPC behaviors for large OWGs. BOs are inspired by object-oriented programming and extend the concept of smart objects. Our approach promotes encapsulation of data and code for multiple related behaviors in one place, hiding internal details and embedding intelligence in the environment. BOs are a natural abstraction of five different techniques that we have implemented to manage AI complexity in an upcoming AAA OWG. We report the details of the implementations in the context of behavior trees and the lessons learned during development. Our study should serve as an inspiration for AI architecture designers from both the academia and the industry.","PeriodicalId":49192,"journal":{"name":"IEEE Transactions on Computational Intelligence and AI in Games","volume":"76 1","pages":"166-180"},"PeriodicalIF":0.0,"publicationDate":"2015-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/TCIAIG.2016.2528499","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"62593398","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}