Procedural Content Generation (PCG) has been a part of video games for the majority of their existence and have been an area of active research over the past decade. How- ever, despite the interest in PCG there is no commonly ac- cepted methodology for assessing and analyzing a generator. Furthermore, the recent trend towards machine learned PCG techniques commonly state the goal of learning the design within the original content, but there has been little assess- ment of whether these techniques actually achieve this goal. This paper presents a number of techniques for the assess- ment and analysis of PCG systems, allowing practitioners and researchers better insight into the strengths and weaknesses of these systems, allowing for better comparison of systems, and reducing the reliance on ad-hoc, cherry-picking-prone tech- niques.
Summerville, Adam (California State Polytechnic University, Pomona ) | Martens, Chris (North Carolina State University) | Samuel, Ben (University of New Orleans) | Osborn, Joseph (Pomona College) | Wardrip-Fruin, Noah (University of California, Santa Cruz) | Mateas, Michael (University of California, Santa Cruz)
Current approaches to game generation don't understand the games they generate. As a result, even the most sophisticated systems in this regard, e.g., Game-o-Matic, betray this problem — generating games with goals that are at odds with their mechanics. We describe Gemini, the first bidirectional game generation and analysis system. Gemini is able to take games as input, perform a proceduralist reading of them, and produce possible interpretations that the games might afford. By utilizing the declarative nature of Answer Set Programming (ASP), this analysis pathway opens up generation of games targeting specific interpretations and makes it possible to ensure the generated games are consistent with the desired reading. For Gemini, we developed a game specification language capable of expressing a larger domain of games than is possible with VGDL, the most widespread representation. We demonstrate the generality of our approach by generating games in a series of domains. These domains are based on prototypes hand-created by a team without knowledge of the constraints and capabilities of Gemini.
We present a new way to represent and understand experience managers - AI agents that tune the parameters of a running game to pursue a designer's goal. Existing representations of AI managers are diverse, which complicates the task of drawing useful comparisons between them. Contrary to previous representations, ours uses a point of unity as its basis: that every game/manager pair can be viewed as only a game with the manager embedded inside. From this basis, we show that several common, differently-represented concepts of experience management can be re-expressed in a unified way. We demonstrate our new representation concretely by comparing two different representations, Search-Based Drama Management and Generalized Experience Management, and we present the insights that we have gained from this effort.
Within the area of procedural content generation (PCG) there are a wide range of techniques that have been used to generate content. Many of these techniques use traditional artificial intelligence approaches, such as genetic algorithms, planning, and answer-set programming. One area that has not been widely explored is straightforward combinatorial search -- exhaustive enumeration of the entire design space or a significant subset thereof. This paper synthesizes literature from mathematics and other subfields of Artificial Intelligence to provide reference for the algorithms needed when approaching exhaustive procedural content generation. It builds on this with algorithms for exhaustive search and complete examples how they can be applied in practice.
Players of digital games face numerous choices as to what kind of games to play and what kind of game content or in-game activities to opt for. Among these, game content plays an important role in keeping players engaged so as to increase revenues for the gaming industry. However, while nowadays a lot of game content is generated using procedural content generation, automatically determining the kind of content that suits players' skills still poses challenges to game developers. Addressing this challenge, we present matrix- and tensor factorization based game content recommender systems for recommending quests in a single player role-playing game. We discuss the theory behind latent factor models for recommender systems and derive an algorithm for tensor factorizations to decompose collections of bipartite matrices. Extensive online bucket type tests reveal that our novel recommender system retained more players and recommended more engaging quests than handcrafted content-based and previous collaborative filtering approaches.
The ability of digital storytelling agents to evaluate their output is important for ensuring high-quality human-agent interactions. However, evaluating stories remains an open problem. Past evaluative techniques are either model-specific--- which measure features of the model but do not evaluate the generated stories ---or require direct human feedback, which is resource-intensive. We introduce a number of story features that correlate with human judgments of stories and present algorithms that can measure these features. We find this approach results in a proxy for human-subject studies for researchers evaluating story generation systems.
Partlan, Nathan (Northeastern University) | Carstensdottir, Elin (Northeastern University) | Snodgrass, Sam (Northeastern University) | Kleinman, Erica (Northeastern University) | Smith, Gillian (Worcester Polytechnic Institute) | Harteveld, Casper (Northeastern University) | El-Nasr, Magy Seif (Northeastern University)
Analysis of interactive narrative is a complex undertaking, requiring understanding of the narrative's design, its affordances, and its impact on players. Analysis is often performed by an expert, but this is expensive and difficult for complex interactive narratives. Automated analysis of structure, the organization of interaction elements, could help augment an expert's analysis. For this purpose we developed a model consisting of a set of metrics to analyze interactive narrative structure, enabled by a novel multi-graph representation. We implemented this model for an interactive scenario authoring tool called StudyCrafter and analyzed 20 student-designed scenarios. We show that the model illuminates the structures and groupings of the scenarios. This work provides insight for manual analysis of attributes of interactive narratives and a starting point for automated design assistance.
Oliveira, Victor M. (Universidade Federal de Goias) | Nascimento, Hugo A. D. do (Universidade Federal de Goias) | Soares, Fabrizzio A. A. M. N. (Universidade Federal de Goias) | Rocha, Cleomar S. (Universidade Federal de Goias)
In the present paper we explore the idea of combining computation power and the availability of ordinary art spectators in order to produce new interactive art works. This is investigated for a particular application, which consists of producing new behaviors for a programmable art apparatus named C3 Cubes. Given the nature of the problem and some difficult challenges to be dealt with, an Interactive Evolutionary Computation (IEC) approach was devised. Furthermore, it was necessary to adopt a surrogate function method for approximating the user's preferences and to implement a Web-based virtual simulation environment for speeding up the generation and the evaluation of C3 Cubes projects. The integration of all these elements is crucial for producing new user-guided cube projects with interesting behaviors. The main approaches experimented in this research and the proposed design solutions are useful to solving similar problems in other domain areas, for example, in the context of game design.
Moraes, Rubens O. (Universidade Federal de Viçosa) | Mariño, Julian R. H. (Universidade de São Paulo) | Lelis, Levi H. S. (Universidade Federal de Viçosa) | Nascimento, Mario A. (University of Alberta)
Search algorithms based on combinatorial multi-armed bandits (CMABs) are promising for dealing with state-space sequential decision problems. However, current CMAB-based algorithms do not scale to problem domains with very large actions spaces, such as real-time strategy games played in large maps. In this paper we introduce CMAB-based search algorithms that use action abstraction schemes to reduce the action space considered during search. One of the approaches we introduce use regular action abstractions (A1N), while the other two use asymmetric action abstractions (A2N and A3N). Empirical results on MicroRTS show that A1N, A2N, and A3N are able to outperform an existing CMAB-based algorithm in matches played in large maps, and A3N is able to outperform all state-of-the-art search algorithms tested.
The ability to extract the sequence of game events for a given player's play-through has traditionally required access to the game's engine or source code. This serves as a barrier to researchers, developers, and hobbyists who might otherwise benefit from these game logs. In this paper we present two approaches to derive game logs from game video via convolutional neural networks and transfer learning. We evaluate the approaches in a Super Mario Bros. clone, Mega Man and Skyrim. Our results demonstrate our approach outperforms random forest and other transfer baselines.