Motivated by applications in electronic games as well as teaching systems, we investigate the problem of dynamic difficulty adjustment. The task here is to repeatedly find a game difficulty setting that is neither too easy' and bores the player, nor too difficult' and overburdens the player. The contributions of this paper are ( i) formulation of difficulty adjustment as an online learning problem on partially ordered sets, ( ii) an exponential update algorithm for dynamic difficulty adjustment, ( iii) a bound on the number of wrong difficulty settings relative to the best static setting chosen in hindsight, and ( iv) an empirical investigation of the algorithm when playing against adversaries.

Appropriately balancing a videogame's difficulty is essential to provide players with a pleasant experience. In a recent study, Korean scientists developed a novel approach for dynamic difficulty adjustment where the players' emotions are estimated using in-game data, and the difficulty level is tweaked accordingly to maximize player satisfaction. Their efforts could contribute to balancing the difficulty of games and making them more appealing to all types of players. Difficulty is a tough aspect to balance in video games. Some people prefer video games that present a challenge whereas others enjoy an easy experience.

Artificial intelligence (AI) has achieved superhuman performance in board games such as Go, chess, and Othello (Reversi). In other words, AI has become too strong an opponent for human players in such games. In this context, it is difficult for a human player to enjoy playing the games with the AI. To keep human players entertained and immersed in a game, the AI is required to dynamically balance its skill with that of the human player. To address this issue, we propose AlphaDDA, an AlphaZero-based AI with dynamic difficulty adjustment (DDA). AlphaDDA consists of a deep neural network (DNN) and a Monte Carlo tree search, as in AlphaZero. AlphaDDA estimates the value of the game state from only the board state using the DNN and changes its skill according to the value. AlphaDDA can adjust its skill using only the state of a game without any prior knowledge regarding an opponent. In this study, AlphaDDA plays Connect4, Othello, and 6x6 Othello, which is Othello using a 6x6 size board, with other AI agents. The other AI agents are AlphaZero, Monte Carlo tree search, the minimax algorithm, and a random player. This study shows that AlphaDDA can balance its skill with that of the other AI agents, except for a random player. The DDA ability of AlphaDDA is derived from an accurate estimation of the value from the state of a game. We believe that the AlphaDDA approach can be used for any game in which the DNN can estimate the value from the state.

Successful and accurate modelling of level difficulty is a fundamental component of the operationalisation of player experience as difficulty is one of the most important and commonly used signals for content design and adaptation. In games that feature intermediate milestones, such as completable areas or levels, difficulty is often defined by the probability of completion or completion rate; however, this operationalisation is limited in that it does not describe the behaviour of the player within the area. In this research work, we formalise a model of level difficulty for puzzle games that goes beyond the classical probability of success. We accomplish this by describing the distribution of actions performed within a game level using a parametric statistical model thus creating a richer descriptor of difficulty. The model is fitted and evaluated on a dataset collected from the game Lily's Garden by Tactile Games, and the results of the evaluation show that the it is able to describe and explain difficulty in a vast majority of the levels.

In games (as well as many user-facing systems), adapting content to user's preferences and experience is an important challenge. This paper explores a novel method to realize this goal in the context of dynamic difficulty adjustment (DDA). Here the aim is to constantly adapt the content of a game to the skill level of the player, keeping them engaged by avoiding states that are either too difficult or too easy. Current systems for DDA rely on expensive data mining, or on hand-crafted rules designed for particular domains, and usually adapts to keep players in the flow, leaving no room for the designer to present content that is purposefully easy or difficult. This paper presents a Bayesian Optimization-based system for DDA that is agnostic to the domain and that can target particular difficulties. We deploy this framework in two different domains: the puzzle game Sudoku, and a simple Roguelike game. By modifying the acquisition function's optimization, we are reliably able to present a puzzle with a bespoke difficulty for players with different skill levels in less than five iterations (for Sudoku) and fifteen iterations (for the simple Roguelike), significantly outperforming simpler heuristics for difficulty adjustment in said domains, with the added benefit of maintaining a model of the user. These results point towards a promising alternative for content adaption in a variety of different domains.

Three Californians say that the video game publisher Electronic Arts is secretly manipulating them. On Nov. 9, they filed a class-action lawsuit accusing EA of surreptitiously using a patented A.I. technology known as dynamic difficulty adjustment in its FIFA, Madden, and NHL games--three of the biggest sports games on the planet. The lawsuit claims EA is using the technology to unfairly increase the difficulty of multiplayer mode online matches in order to encourage players to spend real-world money to boost their chances of winning. EA has denied ever implementing the technology and has called the lawsuit "baseless." For years, players have been stewing over ideas of fairness and balance in games, feeling taken for granted at best and taken advantage of at worst. The class-action complaint, Zajonc et al. v. Electronic Arts, doesn't contain any evidence for its claim, but that's fairly typical for this sort of class-action complaint.

Videogames are nowadays one of the biggest entertainment industries in the world. Being part of this industry means competing against lots of other companies and developers, thus, making fanbases of vital importance. They are a group of clients that constantly support your company because your video games are fun. Videogames are most entertaining when the difficulty level is a good match for the player's skill, increasing the player engagement. However, not all players are equally proficient, so some kind of difficulty selection is required. In this paper, we will present Dynamic Difficulty Adjustment (DDA), a recently arising research topic, which aims to develop an automated difficulty selection mechanism that keeps the player engaged and properly challenged, neither bored nor overwhelmed. We will present some recent research addressing this issue, as well as an overview of how to implement it. Satisfactorily solving the DDA problem directly affects the player's experience when playing the game, making it of high interest to any game developer, from independent ones, to 100 billion dollar businesses, because of the potential impacts in player retention and monetization.

Methods for dynamic difficulty adjustment allow games to be tailored to particular players to maximize their engagement. However, current methods often only modify a limited set of game features such as the difficulty of the opponents, or the availability of resources. Other approaches, such as experience-driven Procedural Content Generation (PCG), can generate complete levels with desired properties such as levels that are neither too hard nor too easy, but require many iterations. This paper presents a method that can generate and search for complete levels with a specific target difficulty in only a few trials. This advance is enabled by through an Intelligent Trial-and-Error algorithm, originally developed to allow robots to adapt quickly. Our algorithm first creates a large variety of different levels that vary across predefined dimensions such as leniency or map coverage. The performance of an AI playing agent on these maps gives a proxy for how difficult the level would be for another AI agent (e.g. one that employs Monte Carlo Tree Search instead of Greedy Tree Search); using this information, a Bayesian Optimization procedure is deployed, updating the difficulty of the prior map to reflect the ability of the agent. The approach can reliably find levels with a specific target difficulty for a variety of planning agents in only a few trials, while maintaining an understanding of their skill landscape.

Motivated by applications in electronic games as well as teaching systems, we investigate the problem of dynamic difficulty adjustment. The task here is to repeatedly find a game difficulty setting that is neither too easy' and bores the player, nor too difficult' and overburdens the player. The contributions of this paper are ($i$) formulation of difficulty adjustment as an online learning problem on partially ordered sets, ($ii$) an exponential update algorithm for dynamic difficulty adjustment, ($iii$) a bound on the number of wrong difficulty settings relative to the best static setting chosen in hindsight, and ($iv$) an empirical investigation of the algorithm when playing against adversaries. Papers published at the Neural Information Processing Systems Conference.

Games have been a major focus of AI since the field formed seventy years ago. Recently, video games have replaced chess and go as the current "Mt. Everest Problem." This paper looks beyond the video games themselves to the application of AI techniques within the ecosystems that produce them. Electronic Arts (EA) must deal with AI at scale across many game studios as it develops many AAA games each year, and not a single, AI-based, flagship application. EA has adopted a horizontal scaling strategy in response to this challenge and built a platform for delivering AI artifacts anywhere within EA's software universe. By combining a data warehouse for player history, an Agent Store for capturing processes acquired through machine learning, and a recommendation engine as an action layer, EA has been delivering a wide range of AI solutions throughout the company during the last two years. These solutions, such as dynamic difficulty adjustment, in-game content and activity recommendations, matchmaking, and game balancing, have had major impact on engagement, revenue, and development resources within EA.