Showing papers in "IEEE Transactions on Computational Intelligence and AI in Games in 2013"
••
TL;DR: An overview of the existing work on AI for real-time strategy (RTS) games focuses on the work around the game StarCraft, which has emerged in the past few years as the unified test bed for this research.
Abstract: This paper presents an overview of the existing work on AI for real-time strategy (RTS) games. Specifically, we focus on the work around the game StarCraft, which has emerged in the past few years as the unified test bed for this research. We describe the specific AI challenges posed by RTS games, and overview the solutions that have been explored to address them. Additionally, we also present a summary of the results of the recent StarCraft AI competitions, describing the architectures used by the participants. Finally, we conclude with a discussion emphasizing which problems in the context of RTS game AI have been solved, and which remain open.
401 citations
••
TL;DR: The appropriateness of game genres (a category of games characterized by a particular set of gameplay challenges) and the associated gameplay challenges for different BCI paradigms is evaluated and a number of recommendations for the field relating to genre-specific BCI-games development and assessing user performance are provided.
Abstract: Brain-computer interfaces (BCIs) and basic computer games have been interconnected since BCI development began, exploiting gameplay elements as a means of enhancing performance in BCI training protocols and entertaining and challenging participants while training to use a BCI. By providing the BCI user with an entertaining environment, researchers hope to assist users in becoming more proficient at controlling a BCI system. BCIs have been used to enrich the experience of abled-bodied and physically impaired users in various computer applications, in particular, computer games. BCI games have been reviewed previously, yet a critical evaluation of “gameplay” within BCI games has not been undertaken. Gameplay is a key aspect of any computer game and encompasses the challenges presented to the player, the actions made available to the player by the game designer to overcome the challenges and the interaction mechanism in the game. Here, the appropriateness of game genres (a category of games characterized by a particular set of gameplay challenges) and the associated gameplay challenges for different BCI paradigms is evaluated. The gameplay mechanics employed across a range of BCI games are reviewed and evaluated in terms of the BCI control strategy's suitability, considering the genre and gameplay mechanics employed. A number of recommendations for the field relating to genre-specific BCI-games development and assessing user performance are also provided for BCI game developers.
193 citations
••
TL;DR: Taking together the results suggest that multiuser BCI applications can be operational, effective, and more engaging for participants.
Abstract: How can we connect two brains to a video game by means of a brain-computer interface (BCI), and what will happen when we do so? How will the two users behave, and how will they perceive this novel common experience? In this paper, we are concerned with the design and evaluation of multiuser BCI applications. We created a multiuser videogame called BrainArena in which two users can play a simple football game by means of two BCIs. They can score goals on the left or right side of the screen by simply imagining left or right hand movements. To add another interesting element, the gamers can play in a collaborative manner (their two mental activities are combined to score in the same goal), or in a competitive manner (the gamers must push the ball in opposite directions). Two experiments were conducted to evaluate the performance and subjective experience of users in the different conditions. In the first experiment, we compared a single-user situation with one multiuser situation: the collaborative task. Experiment 1 showed that multiuser conditions are significantly preferred, in terms of fun and motivation, compared to the single-user condition. The performance of some users was even significantly improved in the multiuser condition. A subset of well-performing subjects was involved in the second experiment, where we added the competitive task. Experiment 2 suggested that competitive and collaborative conditions may lead to similar performances and motivations. However, the corresponding gaming experiences can be perceived differently among the participants. Taken together our results suggest that multiuser BCI applications can be operational, effective, and more engaging for participants.
154 citations
••
TL;DR: It is suggested that BCI as an additional control can be as much fun and natural to use as keyboard/mouse control, even if the amount of control is limited.
Abstract: Brain-computer interfaces (BCIs) are not only being developed to aid disabled individuals with motor substitution, motor recovery, and novel communication possibilities, but also as a modality for healthy users in entertainment and gaming. This study investigates whether the incorporation of a BCI in the popular game World of Warcraft (WoW) has effects on the user experience. A BCI control channel based on parietal alpha band power is used to control the shape and function of the avatar in the game. In the experiment, participants (n=42) , a mix of experienced and inexperienced WoW players, played with and without the use of BCI in a within-subjects design. Participants themselves could indicate when they wanted to stop playing. Actual and estimated duration was recorded and questionnaires on presence and control were administered. Afterwards, oral interviews were taken. No difference in actual duration was found between conditions. Results indicate that the difference between estimated and actual duration was not related to user experience but was person specific. When using a BCI, control and involvement were rated lower. But BCI control did not significantly decrease fun. During interviews, experienced players stated that they saw potential in the application of BCIs in games with complex interfaces such as WoW. This study suggests that BCI as an additional control can be as much fun and natural to use as keyboard/mouse control, even if the amount of control is limited.
119 citations
••
TL;DR: It is argued that a personalized system could be implemented in a consumer context and research should aim at improving classifiers that can be trained online by end users.
Abstract: Passive brain-computer interaction (BCI) can provide useful information to understand a user's state and anticipate intentions, which is needed to support adaptivity and personalization Given the huge variety of audiences, a game's capability of adapting to different user profiles-in particular to keep the player in flow-is crucial to make it ever more enjoyable and satisfying We have performed a user experiment exploiting a four-electrode electroencephalogram (EEG) tool similar to the ones that are soon likely to appear in the market for game control We have performed a spectral characterization of the video-gaming experience, also in comparison with other tasks Results show that the most informative frequency bands for discriminating among gaming conditions are around low beta Simple signals from the peripheral nervous system add marginal information Classification of three levels of user states is possible, with good accuracy, using a support vector machine (SVM) classifier A user-independent classification performs worse than a user-dependent approach (501% versus 664% rate) Personalized SVM training and validation time is reasonable (7-8 min) Thus, we argue that a personalized system could be implemented in a consumer context and research should aim at improving classifiers that can be trained online by end users
115 citations
••
TL;DR: The broader use of the P300 BCI in BCI-controlled video games is recommended, because it exhibits relatively high speed and accuracy, and can be used without user training, after a short calibration.
Abstract: The P300-based brain-computer interface (P300 BCI) is currently a very popular topic in assistive technology development. However, only a few simple P300 BCI-based games have been designed so far. Here, we analyze the shortcomings of this BCI in gaming applications and show that solutions for overcoming them already exist, although these techniques are dispersed over several different games. Additionally, new approaches to improve the P300 BCI accuracy and flexibility are currently being proposed in the more general P300 BCI research. The P300 BCI, even in its current form, not only exhibits relatively high speed and accuracy, but also can be used without user training, after a short calibration. Taking these facts together, the broader use of the P300 BCI in BCI-controlled video games is recommended.
84 citations
••
TL;DR: The results showed that the use of a secondary motor task, in this case the joystick control, did not deteriorate the BCI performance during the game, and concluded that the chosen approach is a suitable multimodal or hybrid BCI implementation, in which the user can even perform other tasks in parallel.
Abstract: In this paper, we describe a multimodal brain-computer interface (BCI) experiment, situated in a highly immersive CAVE. A subject sitting in the virtual environment controls the main character of a virtual reality game: a penguin that slides down a snowy mountain slope. While the subject can trigger a jump action via the BCI, additional steering with a game controller as a secondary task was tested. Our experiment profits from the game as an attractive task where the subject is motivated to get a higher score with a better BCI performance. A BCI based on the so-called brain switch was applied, which allows discrete asynchronous actions. Fourteen subjects participated, of which 50% achieved the required performance to test the penguin game. Comparing the BCI performance during the training and the game showed that a transfer of skills is possible, in spite of the changes in visual complexity and task demand. Finally and most importantly, our results showed that the use of a secondary motor task, in our case the joystick control, did not deteriorate the BCI performance during the game. Through these findings, we conclude that our chosen approach is a suitable multimodal or hybrid BCI implementation, in which the user can even perform other tasks in parallel.
79 citations
••
TL;DR: A game in which the player navigates an avatar through a maze by using a brain-computer interface that analyzes the steady-state visual evoked potential (SSVEP) responses recorded with electroencephalography on the player's scalp is introduced.
Abstract: In this paper, we introduce a game in which the player navigates an avatar through a maze by using a brain-computer interface (BCI) that analyzes the steady-state visual evoked potential (SSVEP) responses recorded with electroencephalography (EEG) on the player's scalp. The four-command control game, called The Maze, was specifically designed around an SSVEP BCI and validated in several EEG setups when using a traditional electrode cap with relocatable electrodes and a consumer-grade headset with fixed electrodes (Emotiv EPOC). We experimentally derive the parameter values that provide an acceptable tradeoff between accuracy of game control and interactivity, and evaluate the control provided by the BCI during gameplay. As a final step in the validation of the game, a population study on a broad audience was conducted with the EPOC headset in a real-world setting. The study revealed that the majority (85%) of the players enjoyed the game in spite of its intricate control (mean accuracy 80.37%, mean mission time ratio 0.90). We also discuss what to take into account while designing BCI-based games.
61 citations
••
TL;DR: A large set of crowdsourced gameplay data of a clone of the classic platform game Super Mario Bros is mined, and dissimilar types of features are explored, including direct measurements of event and item frequencies, and features constructed through frequent sequence mining.
Abstract: What are the aesthetics of platform games and what makes a platform level engaging, challenging, and/or frustrating? We attempt to answer such questions through mining a large set of crowdsourced gameplay data of a clone of the classic platform game Super Mario Bros (SMB). The data consist of 40 short game levels that differ along six key level design parameters. Collectively, these levels are played 1560 times over the Internet, and the perceived experience is annotated by experiment participants via self-reported ranking (pairwise preferences). Given the wealth of this crowdsourced data, as all details about players' in-game behavior are logged, the problem becomes one of extracting meaningful numerical features at the appropriate level of abstraction for the construction of generic computational models of player experience and, thereby, game aesthetics. We explore dissimilar types of features, including direct measurements of event and item frequencies, and features constructed through frequent sequence mining, and go through an in-depth analysis of the interrelationship between level content, players' behavioral patterns, and reported experience. Furthermore, the fusion of the extracted features allows us to predict reported player experience with a high accuracy, even from short game segments. In addition to advancing our insight on the factors that contribute to platform game aesthetics, the results are useful for the personalization of game experience via automatic game adaptation.
58 citations
••
TL;DR: Insight is gained into new biosignal processing algorithms, tested in gaming applications, which exploit BCI and neural signals to enhance gameplay experience and playermotivation, be the players ablebodied or physically impaired.
Abstract: While, to date, there has been successful research into brain-computer game interaction (BCGI), the algorithms and techniques developed are limited in scope and may not utilize all available data in the appropriate contexts, e.g., optimizing for genre-specific games. This special issue was, therefore, solicited to gain insights into new biosignal processing algorithms, tested in gaming applications, which exploit BCI and neural signals to enhance gameplay experience and playermotivation, be the players ablebodied or physically impaired. A snapshot of the current trends in BCIcontrolled computer games is presented across 11 manuscripts. Each is briefly summarized in this editorial introduction.
37 citations
••
TL;DR: The NeuroBot system, which uses a global workspace architecture, implemented in spiking neurons, to control an avatar within the Unreal Tournament 2004 (UT2004) computer game, is designed to display humanlike behavior within UT2004.
Abstract: This paper describes the NeuroBot system, which uses a global workspace architecture, implemented in spiking neurons, to control an avatar within the Unreal Tournament 2004 (UT2004) computer game This system is designed to display humanlike behavior within UT2004, which provides a good environment for comparing human and embodied AI behavior without the cost and difficulty of full humanoid robots Using a biologically inspired approach, the architecture is loosely based on theories about the high-level control circuits in the brain, and it is the first neural implementation of a global workspace that has been embodied in a complex dynamic real-time environment NeuroBot's humanlike behavior was tested by competing in the 2011 BotPrize competition, in which human judges play UT2004 and rate the humanness of other avatars that are controlled by a human or a bot NeuroBot came a close second, achieving a humanness rating of 36%, while the most human human reached 67% We also developed a humanness metric that combines a number of statistical measures of an avatar's behavior into a single number In our experiments with this metric, NeuroBot was rated as 33% human, and the most human human achieved 73%
••
TL;DR: Preliminary results are presented indicating that the BCI interaction is interesting but very tiring and imprecise, and may be better suited as an optional and complementary modality to other interaction techniques.
Abstract: This paper evaluates the usability and efficiency of three multimodal combinations of brain-computer interface (BCI) and eye tracking in the context of a simple puzzle game involving tile selection and rotations using affordable consumer-grade hardware. It presents preliminary results indicating that the BCI interaction is interesting but very tiring and imprecise, and may be better suited as an optional and complementary modality to other interaction techniques.
••
TL;DR: A job-level proof number search (JL-PNS) is presented, a kind of generic job- level search for solving computer game search problems, and some policies are proposed, such as virtual win, virtual loss, virtual equivalence, flagging, or hybrids of the above, to expand the nodes.
Abstract: This paper introduces an approach, called generic job-level search, to leverage the game-playing programs which are already written and encapsulated as jobs. Such an approach is well suited to a distributed computing environment, since these jobs are allowed to be run by remote processors independently. In this paper, we present and focus on a job-level proof number search (JL-PNS), a kind of generic job-level search for solving computer game search problems, and apply JL-PNS to solving automatically several Connect6 positions, including some difficult openings. This paper also proposes a method of postponed sibling generation to generate nodes smoothly, and some policies, such as virtual win, virtual loss, virtual equivalence, flagging, or hybrids of the above, to expand the nodes. Our experiment compared these policies, and the results showed that the virtual-equivalence policy, together with flagging, performed the best against other policies. In addition, the results also showed that the speedups for solving these positions are 8.58 on average on 16 cores.
••
TL;DR: Results from an experimental study with able-bodied subjects playing a virtual ball game suggest that the Kinect sensor is useful for isolating specific movements during the interaction with the game, and that the computed EEG patterns for hand and feet movements are in agreement with results described in the literature.
Abstract: The use of statistical models and statistical inference for characterizing the interplay between brain structures and human behavior (functional brain mapping) is common in neuroscience. Statistical methods, however, require the availability of sufficiently large data sets. As a result, experimental paradigms used to collect behavioral trials from individuals are data centered and not user centered. This means that experimental paradigms are tuned to collect as many trials as possible, are generally rather demanding, and are not always motivating or engaging for individuals. Subject cooperation and their compliance with the task may decrease over time. Whenever possible, paradigms are designed to control for factors such as fatigue, attention, and motivation. In this paper, we propose the use of the Kinect motion tracking sensor (Microsoft, Inc., Redmond, WA, USA) in a game-based paradigm for noninvasive electroencephalogram (EEG)-based functional motor mapping. Results from an experimental study with able-bodied subjects playing a virtual ball game suggest that the Kinect sensor is useful for isolating specific movements during the interaction with the game, and that the computed EEG patterns for hand and feet movements are in agreement with results described in the literature.
••
TL;DR: It is demonstrated that although evolutionary-based methods yield players that fare best against a fixed heuristic player, it is the coev evolutionary temporal difference learning (CTDL), a hybrid of coevolution and TDL, that generalizes better and proves superior when confronted with a pool of previously unseen opponents.
Abstract: This study investigates different methods of learning to play the game of Othello. The main questions posed concern scalability of algorithms with respect to the search space size and their capability to generalize and produce players that fare well against various opponents. The considered algorithms represent strategies as n-tuple networks, and employ self-play temporal difference learning (TDL), evolutionary learning (EL) and coevolutionary learning (CEL), and hybrids thereof. To assess the performance, three different measures are used: score against an a priori given opponent (a fixed heuristic strategy), against opponents trained by other methods (round-robin tournament), and against the top-ranked players from the online Othello League. We demonstrate that although evolutionary-based methods yield players that fare best against a fixed heuristic player, it is the coevolutionary temporal difference learning (CTDL), a hybrid of coevolution and TDL, that generalizes better and proves superior when confronted with a pool of previously unseen opponents. Moreover, CTDL scales well with the size of representation, attaining better results for larger n-tuple networks. By showing that a strategy learned in this way wins against the top entries from the Othello League, we conclude that it is one of the best 1-ply Othello players obtained to date without explicit use of human knowledge.
••
TL;DR: A new approach is presented that guarantees coverage by abstracting the search space, using the same algorithm that performs the real-time search, and reduces the precomputation time via the use of dynamic programming.
Abstract: Real-time heuristic search algorithms satisfy a constant bound on the amount of planning per action, independent of the problem size. These algorithms are useful when the amount of time or memory resources are limited, or a rapid response time is required. An example of such a problem is pathfinding in video games where numerous units may be simultaneously required to react promptly to a player's commands. Classic real-time heuristic search algorithms cannot be deployed due to their obvious state revisitation (“scrubbing”). Recent algorithms have improved performance by using a database of precomputed subgoals. However, a common issue is that the precomputation time can be large, and there is no guarantee that the precomputed data adequately cover the search space. In this paper, we present a new approach that guarantees coverage by abstracting the search space, using the same algorithm that performs the real-time search. It reduces the precomputation time via the use of dynamic programming. The new approach eliminates the learning component and the resultant “scrubbing.” Experimental results on maps of tens of millions of grid cells from Counter-Strike: Source and benchmark maps from Dragon Age: Origins show significantly faster execution times and improved optimality results compared to previous real-time algorithms.
••
TL;DR: An application of Monte Carlo tree search (MCTS) to control ghosts in the game called Ms. Pac-Man is presented and a mechanism for predicting Ms.Pac-Man's future movements is introduced to increase the reliability of MCTS results.
Abstract: In this paper, we present an application of Monte Carlo tree search (MCTS) to control ghosts in the game called Ms Pac-Man Our proposed ghost team consists of a ghost controlled by rules and three ghosts controlled individually by different MCTS Given a limited time response, in order to increase the reliability of MCTS results, we introduce a mechanism for predicting Ms Pac-Man's future movements and use this mechanism for simulating Ms Pac-Man during Monte Carlo simulations Our ghost team won the first Ms Pac-Man Versus Ghost Team Competition at the 2011 IEEE Congress on Evolutionary Computation (CEC) Its performances for a variety of design choices are also shown and discussed
••
TL;DR: This study explores a novel, context-dependant, approach for a steady-state visual-evoked potential (SSVEP)-based BCI controller that has been integrated within a BCI computer game and its influence in performance and mental workload has been addressed through a pilot experiment.
Abstract: Brain-computer interfaces (BCIs) are becaming more available to the general public, and have already been used to control applications such as computer games. One disadvantage is that they are not completely reliable. In order to increase BCI performances, some low-level adjustments can be made, such as signal processing, as well as high level adjustments such as modifying the controller paradigm. In this study, we explore a novel, context-dependant, approach for a steady-state visual-evoked potential (SSVEP)-based BCI controller. This controller uses two kinds of behavior alternation: commands can be added and removed if their use is irrelevant to the context and the actions resulting from their activation can be weighted depending on the likeliness of the actual intention of the user. This controller has been integrated within a BCI computer game and its influence in performance and mental workload has been addressed through a pilot experiment. Preliminary results have shown a workload reduction and performance improvement with the context-dependent controller, while keeping the engagement levels untouched.
••
TL;DR: Control of a tactile ERP-BCI in a dual-task situation is feasible, but performance is degraded, and reallocation of attention caused by a concurrent task, but unaffected by task difficulty, is discussed.
Abstract: When using brain-computer interfaces (BCIs) to control a game, the BCI may have to compete with gaming tasks for the same perceptual and cognitive resources. We investigated: 1) if and to what extent event-related potentials (ERPs) and ERP-BCI performance are affected in a dual-task situation; and 2) if these effects are an area function of the level of difficulty of a concurrent task. Ten participants performed an ERP-BCI task that involved attending to a target location in sequences of tactile stimuli. The ERP-BCI task was performed either in isolation or secondary to a visual n-back task with two levels of difficulty. We observed: 1) a decreased P300 and BCI bit rate, and an increased level of subjective mental effort for both dual-task conditions compared to the BCI-only condition; the decreased classification accuracies were still well above chance, but arguably too low for effective BCI control; and 2) we did not find an effect of task difficulty on the P300, bit rates, and subjective mental effort. We discuss reallocation of attention caused by a concurrent task, but unaffected by task difficulty, and the role of task priority. Concluding, control of a tactile ERP-BCI in a dual-task situation is feasible, but performance is degraded.
••
TL;DR: An overview of general purpose computing on graphics processor units (GPGPU computing) is presented, beginning with early shader language solutions and continuing to discuss three accessible platforms for GPGPU development: CUDA, OpenCL, and Direct Compute.
Abstract: This paper reviews developments in general purpose computing on graphics processor units (GPGPU computing) from the perspective of video-game-related artificial intelligence (AI). We present an overview of the field, beginning with early shader language solutions and continuing to discuss three accessible platforms for GPGPU development: CUDA, OpenCL, and Direct Compute. Consideration is given to the commercial and practical realities which hinder the adoption of GPGPU solutions within video game AI, and developments in GPGPU computing directly relevant to common AI practices within the video games industry are reviewed in depth.
••
TL;DR: This work proposes an MCS algorithm discovery scheme that introduces a grammar over MCS algorithms that enables inducing a rich space of candidate algorithms and relies on multiarmed bandits to approximately solve this optimization problem.
Abstract: Much current research in AI and games is being devoted to Monte Carlo search (MCS) algorithms. While the quest for a single unified MCS algorithm that would perform well on all problems is of major interest for AI, practitioners often know in advance the problem they want to solve, and spend plenty of time exploiting this knowledge to customize their MCS algorithm in a problem-driven way. We propose an MCS algorithm discovery scheme to perform this in an automatic and reproducible way. First, we introduce a grammar over MCS algorithms that enables inducing a rich space of candidate algorithms. Afterwards, we search in this space for the algorithm that performs best on average for a given distribution of training problems. We rely on multiarmed bandits to approximately solve this optimization problem. The experiments, generated on three different domains, show that our approach enables discovering algorithms that outperform several well-known MCS algorithms such as upper confidence bounds applied to trees and nested Monte Carlo search. We also show that the discovered algorithms are generally quite robust with respect to changes in the distribution over the training problems.
••
TL;DR: This paper examines a simple 5 × 5 Hex position that not only completely defeats flat Monte Carlo search, but also initially defeats plain upper confidence bounds for trees (UCT) search until an excessive number of iterations are performed.
Abstract: This paper examines a simple 5 × 5 Hex position that not only completely defeats flat Monte Carlo search, but also initially defeats plain upper confidence bounds for trees (UCT) search until an excessive number of iterations are performed. The inclusion of domain knowledge during playouts significantly improves UCT performance, but a slight negative effect is shown for the rapid action value estimate (RAVE) heuristic under some circumstances. This example was drawn from an actual game during standard play, and highlights the dangers of relying on flat Monte Carlo and unenhanced UCT search even for rough estimates. A brief comparison is made with RAVE failure in Go.
••
TL;DR: A fast dynamic programming (DP) method for line solving, whose time complexity in the worst case is O(kl) only, where the grid size is l×l and k is the average number of integers in one constraint, always smaller than l.
Abstract: A nonogram puzzle is played on a rectangular grid of pixels with clues given in the form of row and column constraints. The aim of solving a nonogram puzzle, an NP-complete problem, is to paint all the pixels of the grid in black and white while satisfying these constraints. This paper proposes an efficient approach to solving nonogram puzzles. We propose a fast dynamic programming (DP) method for line solving, whose time complexity in the worst case is O(kl) only, where the grid size is l×l and k is the average number of integers in one constraint, always smaller than l. In contrast, the time complexity for the best line-solving method in the past is O(kl2). We also propose some fully probing (FP) methods to solve more pixels before running backtracking. Our FP methods can solve more pixels than the method proposed by Batenburg and Kosters (before backtracking), while having a time complexity that is smaller than theirs by a factor of O(l). Most importantly, these FP methods provide useful guidance in choosing the next promising pixel to guess during backtracking. The proposed methods are incorporated into a fast nonogram solver, named LalaFrogKK. The program outperformed all the programs collected in webpbn.com, and also won both nonogram tournaments that were held at the 2011 Conference on Technologies and Applications of Artificial Intelligence (TAAI 2011, Taiwan). We expect that the proposed FP methods can also be applied to solving other puzzles efficiently.
••
TL;DR: This paper develops and compares three automated competition mechanisms, constructed as iterative games, and test them in the context of the aerospace service supply chain, finding that extended Vickrey auctions can handle multiple criteria and provide higher market efficiency at lower computational cost, especially in small to medium markets.
Abstract: Self-serving assets (SSAs) are a new interpretation of the intelligent product technology, set to transform product lifecycle management through automation. SSAs are engineering assets that autonomously monitor their health and expiry dates, search for suppliers, and negotiate with them, while they are still in use by the customer. The concept enables more timely and transparent supplier decision making while eliminating central database transactions and tedious manual effort. Autonomous self-interested agents that act on behalf of their stakeholders naturally give rise to an allocation problem, under the assumption of private information held by trade parties and capacity constrained suppliers providing imperfectly substitutable goods (ISGs). In this paper, we develop and compare three automated competition mechanisms, constructed as iterative games, and test them in the context of the aerospace service supply chain. The competition mechanisms include a prioritized selection mechanism, extended Vickrey, and reverse Dutch auctions. Our context drives us to seek mechanisms that will not only perform well in terms of economic theory, but also in terms of computational performance. Key findings are that extended Vickrey auctions can handle multiple criteria and provide higher market efficiency at lower computational cost, especially in small to medium markets. As scalability is an issue in large markets, the use of auctions is recommended only for complex high value assets or under uncertain market scenarios. As business-to-business (B2B) environments are becoming the norm for many global companies, our study aims to be exemplary to those who would like to implement automated auction mechanisms in highly complex environments.
••
TL;DR: This paper proposes an MCTS improvement, called incentive learning, which learns the default policy online, based on ideas from combinatorial game theory, and hence is particularly useful when the underlying game is a sum of games.
Abstract: Monte Carlo tree search (MCTS) is a search paradigm that has been remarkably successful in computer games like Go. It uses Monte Carlo simulation to evaluate the values of nodes in a search tree. The node values are then used to select the actions during subsequent simulations. The performance of MCTS heavily depends on the quality of its default policy, which guides the simulations beyond the search tree. In this paper, we propose an MCTS improvement, called incentive learning, which learns the default policy online. This new default policy learning scheme is based on ideas from combinatorial game theory, and hence is particularly useful when the underlying game is a sum of games. To illustrate the efficiency of incentive learning, we describe a game named Heap-Go and present experimental results on the game.
••
TL;DR: With this optimization scheme, errors in model fitting were minimized without human intervention, allowing automated reconstruction of 3-D animation from consecutive monocular video frames at high accuracy, and it is demonstrated that information-theoretical evaluation can be an effective approach for model-based reconstruction from single-view videos.
Abstract: Automated 3-D modeling from real sports videos can provide useful resources for visual design in sports-related computer games, saving a lot of effort in manual design of visual contents. However, image-based 3-D reconstruction usually suffers from inaccuracy caused by statistic image analysis. In this paper, we propose an information-theoretical scheme to minimize errors of automated 3-D modeling from monocular sports videos. In the proposed scheme, mutual information (MI) was exploited to compute the fitting scores of a 3-D model against the observed single-view scene, and the optimization of model fitting was carried out subsequently. With this optimization scheme, errors in model fitting were minimized without human intervention, allowing automated reconstruction of 3-D animation from consecutive monocular video frames at high accuracy. In our work, the Snooker videos were taken as our case study, balls were positioned in 3-D space from single-view frames, and 3-D animation was reproduced from real Snooker videos. Our experimental results validated that the proposed information-theoretical scheme can help attain better accuracy in the automated reconstruction of 3-D animation, and demonstrated that information-theoretical evaluation can be an effective approach for model-based reconstruction from single-view videos.
••
TL;DR: The modeling here is complete by introducing significant developments for the high-level planner which guides the precise optimal controller to generate a plan given at any random initial state.
Abstract: In the past , we have proposed a two-layered approach to compute a winning strategy for the game of Billiards. AI tools as well as robust optimization routines for noisy environments were combined to plan the sequence of shots. We complete the modeling here by introducing significant developments for the high-level planner which guides the precise optimal controller to generate a plan given at any random initial state. We will first resume the general model for this particular class of problems and then propose several domain-specific heuristics to guide our search and render the problem tractable. Several improvements to the optimal robust controller, including refinements in the objective function, will also be presented in order to improve single-shot optimization. Results are presented demonstrating the full potential of the methods proposed making it the state of the art in regards to the game of Billiards.
••
TL;DR: Examination of a pure strategy game known as Goofspiel and the results of round-robin competitions between 14 programs designed to play this game, finding no clear dominating strategy of play has emerged.
Abstract: In this paper, we examine a pure strategy game known as Goofspiel and report on the results of round-robin competitions between 14 programs designed to play this game. Goofspiel is a two-person card game that is easy to play. However, playing this game successfully has proven to be a difficult task. There is no known “good” strategy for Goofspiel. This is the first time that playing Goofspiel has been examined in a context of a round-robin competition between programs. None of the participating programs won consistently against its rivals. Thus, no clear dominating strategy of play has emerged. In this respect, Goofspiel is similar to the Prisoner's Dilemma where Tit-for-Tat has proven to be a good strategy against many but not against all. This paper introduces Repeated Goofspiel and presents preliminary experimental results. We hope it will motivate further research into this fascinating game.
••
TL;DR: This paper investigates how the strategy constraints influence the equilibrium and shows how to solve repeated games with strategy constraints by analyzing a repeated battle of the sexes game with a budget constraint.
Abstract: Backward induction has led to some controversy in specific games, the surprise exam paradox and iterated prisoner's dilemma for example, despite its wide use in solving finitely repeated games with complete information. In this paper, a typical misuse of backward induction is revealed by analyzing the surprise exam paradox, and the reason why backward induction may fail is investigated. The surprise exam paradox represents a set of repeated games with strategy constraints and has not been fully investigated in game theory. The agents in real-world activities always face constraints in decision making, for example, a budget limitation. In a repeated game with strategy constraints, the players' choices in different stages are not independent and later choices depend on previous choices because of the strategy constraints. Backward induction cannot be applied in its normal use and it needs to be combined with Bayes' theorem in solving these kinds of problems. We also investigate how the strategy constraints influence the equilibrium and show how to solve repeated games with strategy constraints by analyzing a repeated battle of the sexes game with a budget constraint.
••
TL;DR: The results obtained during the simulations showed that the team (consisting of two players) using the evaluation function with its coefficients optimized by the GA won in more than 69.18% of the total matches.
Abstract: In four-sided Dominos, the popular way of playing Dominos in Amazonas State, in Brazil, the strategies used for the game are more complex than those adopted in the more traditional two-sided Dominos, the most popular domino game played in Brazil. This work presents the optimization of an evaluation function for the best move in four-sided Dominos using a genetic algorithm (GA). The evaluation function comprises terms incorporating game strategies defined as: punctuating, facilitating future moves, and complicating opponents' moves. Coefficients were defined to determine the importance of each term of the evaluation function and a set of parameters and operators for implementing the GA. The players' ability was calculated by the number of wins in 5000 matches. The results obtained during the simulations showed that the team (consisting of two players) using the evaluation function with its coefficients optimized by the GA won in more than 69.18% of the total matches.