Towards a Model-Learning Approach to Interactive Narrative Intelligence for Opportunistic Storytelling (original) (raw)

Semi-automatic task recognition for interactive narratives with EAT & RUN

Proceedings of the Intelligent Narrative Technologies III Workshop on - INT3 '10, 2010

Mining data from online games provides a potential alternative to programming behavior and dialogue for characters in interactive narratives by hand. Human annotation of course-grained tasks can provide explanations that make the data more useful to an AI system, however human labor is expensive. We describe a semiautomatic methodology for recognizing tasks in gameplay traces, including an annotation tool for non-experts, and a runtime algorithm. Our results show that this methodology works well with a large corpus from one game, and suggests the possibility of refactoring the development process for interactive narratives.

Probabilistic goal recognition in interactive narrative environments

2006

Abstract Recent years have witnessed a growing interest in interactive narrative-centered virtual environments for education, training, and entertainment. Narrative environments dynamically craft engaging story-based experiences for users, who are themselves active participants in unfolding stories. A key challenge posed by interactive narrative is recognizing users' goals so that narrative planners can dynamically orchestrate plot elements and character actions to create rich, customized stories.

Non-linear Interactive Storytelling

2004

Narration and interaction are often viewed as contrary properties in computer games. Games with a high degree of interaction fail to provide a coherent narration and the player's interaction seldom has any direct impact on the narrative. Games with a high degree of narration often tells a linear story similar to books or movies with little room for the player to interact. We propose non-linear interactive storytelling (NOLIST) as a first step towards developing games with a high degree of interaction and a coherent narrative. The main idea is that the narrative is not fixed from the beginning but instead constructed as the game progresses based on the player's interaction. We provide a simple model that allows writers to specify a NOLIST as a set of actions which the game engine then combines to create the narrative. Finally, we propose to develop a game engine using Bayesian networks to model the probability of the possible narratives that can be created from the actions, and use this knowledge to create better narratives.

Applying a plan-recognition/plan-generation paradigm to interactive storytelling

2006

A key issue in interactive storytelling is how to generate stories which are, at the same time, interesting and coherent. On the one hand, it is desirable to provide means for the user to intervene in the story. But, on the other hand, it is necessary to guarantee that user intervention will not introduce events that violate the rules of the intended genre. This paper describes the usage of a plan recognition / plan generation paradigm in LOGTELL, a logic-based tool for the interactive generation and dramatization of stories. We focus on the specification of a formal logic model for events and characters' behaviour and on how the tool helps the interactive composition of plots through the adaptation of fully or partially generated plots. Based on the model, the user can interact with the tool at various levels, obtaining a variety of stories agreeable to individual tastes, within the imposed coherence requirements. The system alternates stages of goal inference, planning, plan recognition, user intervention and 3D visualization. Our experiments have shown that the system can be used not only for entertainment purposes but also, more generally, to help in the creation and adaptation of stories in conformity with a specified genre.

Interactive Narrative Personalization with Deep Reinforcement Learning

Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, 2017

Data-driven techniques for interactive narrative generation are the subject of growing interest. Reinforcement learning (RL) offers significant potential for devising data-driven interactive narrative generators that tailor players’ story experiences by inducing policies from player interaction logs. A key open question in RL-based interactive narrative generation is how to model complex player interaction patterns to learn effective policies. In this paper we present a deep RL-based interactive narrative generation framework that leverages synthetic data produced by a bipartite simulated player model. Specifically, the framework involves training a set of Q-networks to control adaptable narrative event sequences with long short-term memory network-based simulated players. We investigate the deep RL framework’s performance with an educational interactive narrative, Crystal Island. Results suggest that the deep RL-based narrative generation framework yields effective personalized int...

Character-driven story generation in interactive storytelling

2001

Abstract We describe a fully implemented prototype for interactive storytelling using the Unreal TM engine. We describe the important mechanisms involved in the variability of plot instantiations, within a scenario of sitcom genre. We also provide an evaluation of the concepts of how the dynamic interactions between agents and/or the user influence the generation of story, with first results of examples

Applying Planning to Interactive Storytelling: Narrative Control using State Constraints

We have seen ten years of the application of AI Planning to the problem of narrative generation in Interactive Storytelling (IS). In that time Planning has emerged as the dominant technology and has featured in a number of prototype systems. Nevertheless key issues remain, such as how best to control the shape of the narrative that is generated (e.g. by using narrative control knowledge, that is, knowledge about narrative features that enhance user experience) and also how best to provide support for real-time interactive performance in order to scale up to more realistic sized systems. Recent progress in Planning technology has opened up new avenues for IS and we have developed a novel approach to narrative generation that builds on this. Our approach is to specify narrative control knowledge for a given story world using state trajectory constraints and then to treat these state constraints as landmarks and to use them to decompose narrative generation in order to address scalability issues and the goal of real-time performance in larger story domains. This approach to narrative generation is fully implemented in an Interactive Narrative based on the Merchant of Venice. The contribution of the work lies both in our novel use of state constraints to specify narrative control knowledge for Interactive Storytelling and also our development of an approach to narrative generation that exploits such constraints. In the paper we show how the use of state constraints can provide a unified perspective on important problems faced in IS.

Narrative Intelligence

Abstract: Research in Artificial Intelligence (AI)--before the so-called 'AI winter'when funding from the military went south--repeatedly engaged with stories: How might one write software to understand and generate narratives? From the time of this 'winter,'roughly the late-1980s, until the mid-1990s, fun topics, like storytelling, were put to the side.

Objective Metrics for Interactive Narrative

Interactive Storytelling, 2014

This paper describes, implements and assesses a series of user-log indicators for automatic interactive narrative evaluation. The indicators include length and duration, diversity, renewal, choice range, choice frequency, and choice variety. Based on a laboratory experiment with players, a significant positive correlation has been observed between two indicators and some aspects of the interactive narrative experience measured by validated scales based on questionnaires.

Planning characters' behaviour in interactive storytelling

2002

Abstract In this paper, we describe a method for implementing the behaviour of artificial actors in the context of interactive storytelling. We have developed a fully implemented prototype based on the Unreal Tournament™ game engine, and carried experiments with a simple sitcom-like scenario. We discuss the central role of artificial actors in interactive storytelling and how real-time generation of their behaviour participates in the creation of a dynamic storyline.