This paper comprehensively reviews the metrics for measuring the diversity of game scenarios, spotlighting the innovative use of procedural content generation and other fields as cornerstones for enriching player experiences through diverse game scenarios. By traversing a wide array of disciplines, from affective modeling and multiagent systems to psychological studies, our research underscores the importance of diverse game scenarios in gameplay and education. Through a taxonomy of diversity metrics and evaluation methods, we aim to bridge the current gaps in literature and practice, offering insights into effective strategies for measuring and integrating diversity in game scenarios. Our analysis highlights the necessity for a unified taxonomy to aid developers and researchers in crafting more engaging and varied game worlds. This survey not only charts a path for future research in diverse game scenarios but also serves as a handbook for industry practitioners seeking to leverage diversity as a key component of game design and development.

The computational modeling of player experience is key to the generation of personalized game content. The notion offun, as one of the most peculiar and core aspects of game experience, has often been modeled and quantified for the purpose of content generation with varying success. Recently, measures of a player'sfunhave been ad-hoc designed to model moderate levels of in-game divergence in platformer games, inspired by Koster'stheory of fun. Such measures have shaped the reward functions of game content generative methods following theexperience-driven procedural content generation via reinforcement learning(EDRL) paradigm inSuper Mario BrosIn this article, we present a comprehensive user study involving over 90 participants with a dual purpose: to evaluate the ad-hocfunmetrics introduced in the literature and test the effectiveness of the EDRL framework to generate personalizedfunSuper Mario Brosexperiences in an online fashion. Our key findings suggest that moderate degrees of game level and gameplay divergence are highly consistent with the perceived notion offunof our participants, cross-verifying the ad-hoc designedfunmetrics. On the other hand, it appears that EDRL generators manage to match the preferred (i.e.,fun) game experiences of each persona, only in part and for some players. Our findings suggest that the use of multifaceted in-game data, such as events and actions, will likely enable the modeling of more nuanced gameplay behaviors. In addition, the verification of player persona modeling and the enhancement of player engagement through dynamic experience modelling are suggested as potential future directions.

Deep reinforcement learning has recently been successfully applied to online procedural content generation in which a policy determines promising game-level segments. However, existing methods can hardly discover diverse level patterns, while the lack of diversity makes the gameplay boring. This paper proposes an ensemble reinforcement learning approach that uses multiple negatively correlated sub-policies to generate different alternative level segments, and stochastically selects one of them following a selector model. A novel policy regularisation technique is integrated into the approach to diversify the generated alternatives. In addition, we develop theorems to provide general methodologies for optimising policy regularisation in a Markov decision process. The proposed approach is compared with several state-of-the-art policy ensemble methods and classic methods on a well-known level generation benchmark, with two different reward functions expressing game-design goals from different perspectives. Results show that our approach boosts level diversity notably with competitive performance in terms of the reward. Furthermore, by varying the regularisation coefficient, the trained generators form a well-spread Pareto front, allowing explicit trade-offs between diversity and rewards of generated levels.

In this paper, we revisit endless online level generation with the recently proposed experience-driven procedural content generation via reinforcement learning (EDRL) framework. Inspired by an observation that EDRL tends to generate recurrent patterns, we formulate a notion ofstate space closurewhich makes any stochastic state appeared possibly in an infinite-horizon online generation process can be found within a finite-horizon. Through theoretical analysis, we find that even though state space closure arises a concern about diversity, it generalises EDRL trained with a finite-horizon to the infinite-horizon scenario without deterioration of content quality. Moreover, we verify the quality and the diversity of contents generated by EDRL via empirical studies, on the widely usedSuper Mario Bros.benchmark. Experimental results reveal that the diversity of levels generated by EDRL is limited due to the state space closure, whereas their quality does not deteriorate in a horizon which is longer than the one specified in the training. Concluding our outcomes and analysis, future work on endless online level generation via reinforcement learning should address the issue of diversity while assuring the occurrence of state space closure and quality.

Reinforcement learning algorithms have performed well in playing challenging board and video games. More and more studies focus on improving the generalisation ability of reinforcement learning algorithms. The GVGAI Learning Competition aims to develop agents capable of learning to play different game levels that were unseen during training. This paper summarises the five years' GVGAI Learning Competition editions. At each edition, three new games were designed. The training and test levels were designed separately in the first three editions. Since 2020, three test levels of each game were generated by perturbing or combining two training levels. Then, we present a novel reinforcement learning technique with dual-observation for general video game playing, assuming that it is more likely to observe similar local information in different levels rather than global information. Instead of directly inputting a single, raw pixel-based screenshot of the current game screen, our proposed general technique takes the encoded, transformed global and local observations of the game screen as two simultaneous inputs, aiming at learning local information for playing new levels. Our proposed technique is implemented with three state-of-the-art reinforcement learning algorithms and tested on the game set of the 2020 GVGAI Learning Competition. Ablation studies show the outstanding performance of using encoded, transformed dual observations as input.

Game consists of multiple types of content, while the harmony of different content types play an essential role in game design. However, most works on procedural content generation consider only one type of content at a time. In this paper, we propose and formulate online level generation from music, in a way of matching a level feature to a music feature in real-time, while adapting to players’ play speed. A generic framework named online player-adaptive procedural content generation via reinforcement learning, OPARL for short, is built upon the experience-driven reinforcement learning and controllable reinforcement learning, to enable online level generation from music. Furthermore, a novel control policy based on local search and k-nearest neighbours is proposed and integrated into OPARL to control the level generator considering the play data collected online. Results of simulation-based experiments show that our implementation of OPARL is competent to generate playable levels with difficulty degree matched to the “energy” dynamic of music for different artificial players in an online fashion.

The recently introduced EDRL framework approaches the experience-driven (ED) procedural generation of game content via a reinforcement learning (RL) perspective. EDRL has so far shown its effectiveness in generating novel platformer game levels endlessly in an online fashion. This paper extends the framework by integrating multiple facets of game creativity in the ED generation process. In particular, we employ EDRL on the creative facets of game level and gameplay design in Super Mario Bros. Inspired by Koster’s theory of fun, we formulate fun as moderate degrees of level or gameplay divergence and equip the algorithm with such reward functions. Moreover, we enable faster and more efficient game content generation through an episodic generative soft actor-critic algorithm. The resulting multifaceted EDRL is not only capable of generating fun levels efficiently, but it is also robust with respect to dissimilar playing styles and initial game level conditions.

The time-series GAN and periodic spatial GAN show different yet competitive performance in terms of the evaluation metrics adopted, their deviation from human-designed danmakus, and the diversity of generated danmakus. The preliminary experimental studies presented here showcase that potential of time-series GANs for sequential content generation in games.

Applying latent variable evolution to game level design has become more and more popular as little human expert knowledge is required. However, defective levels with illegal patterns may be generated due to the violation of constraints for level design. A traditional way of repairing the defective levels is programming specific rule-based repairers to patch the flaw. However, programming these constraints is sometimes complex and not straightforward. An autonomous level repairer which is capable of learning the constraints is needed. In this paper, we propose a novel approach, CNet, to learn the probability distribution of tiles giving its surrounding tiles on a set of real levels, and then detect the illegal tiles in generated new levels. Then, an evolutionary repairer is designed to search for optimal replacement schemes equipped with a novel search space being constructed with the help of CNet and a novel heuristic function. The proposed approaches are proved to be effective in our case study of repairing GAN-generated and artificially destroyed levels of Super Mario Bros. game. Our CNet-assisted evolutionary repairer can also be easily applied to other games of which the levels can be represented by a matrix of objects or tiles.