A Possible Worlds Model of Belief for State-Space Narrative Planning

Planning-based narrative generation is effective at producing stories with a logically-sound flow of events, but it can be limiting due to the rigidity of its constraints and the high burden on the domain author to define story-world objects, initial states, and author and character goals. Giving the system the freedom to add objects and events to the story-world history arbitrarily can improve variety and reduce authorial burden, but risks leading to stories that seem jarringly contrived to the audience. I propose to use question-answering as the antidote to contrivance in a highly-generative interactive narrative system: By modeling the player's beliefs about the story world, inferring the implicit questions the player may be asking through their interactions, and answering those questions in a way consistent with the player's prior knowledge, a system could focus on creating cohesion in the ways that matter most to the player while accepting a degree of contrivance in the details that the player is likely to overlook.

Section: Past Workmentioning

confidence: 99%

Open-World Narrative Generation to Answer Players’ Questions

Siler

2022

“…Cavazza and his collaborators (Cavazza, Charles, and Mead 2003) describe an approach to the generation of story sequences where characters are unaware of some aspects of the world around them, including the harmful consequences of some of their own actions. Shirvani and their collaborators (Shirvani, Ware, and Farrell 2017) propose an extension to state space planning models that represents character beliefs as well. Their approach also tracks character beliefs, only with deeper layers of nested beliefs.…”

Section: Related Workmentioning

confidence: 99%

HeadSpace: Incorporating Action Failure and Character Beliefs into Narrative Planning

Sanghrajka

Young

Thorne

2022

Previous work on story planning has lacked a knowledge representation for characters that attempt actions that fail because of the characters' misconceptions about the world state. This work describes HeadSpace, a state-space heuristic search planning system that generates stories that track and manipulate characters' beliefs about the story world. The planner produces story plans with actions that are attempted but fail. We show an example story plan that contains failed-action content that cannot be generated by typical planning-based approaches to story creation, and we provide an analytical evaluation that characterizes our planner's increased expressive range relative to other narrative planners addressing character belief and/or failed action execution.

“…Teutenberg and Porteous (Teutenberg and Porteous 2015) employ the power of local knowledge for characters to create narrative scenarios where characters can perform deceitful actions such as feign-death. Shirvani et al (Shirvani, Ware, and Farrell 2017) expand the space of generated stories even further by allowing characters to imagine "possible worlds" based on their (possibly inconsistent) beliefs, and act according to their local model of the world. More recently, Christensen et al (Christensen, Nelson, and Cardona-Rivera 2020) propose a domain compilation model that builds in failed actions and different beliefs into a PDDL compilation.…”

Section: Related Workmentioning

confidence: 99%

Evaluating Reader Comprehension of Plan-Based Stories Containing Failed Actions

Sanghrajka

Young

2022

A growing number of algorithms for story planning include the ability to create stories with failed actions -- in particular failed actions that occur because of the mistaken beliefs of the characters attempting them. To date, most of these systems have been evaluated analytically, primarily by comparing their expressive range to prior story generation systems. Empirical evaluation of these systems has been preliminary. In this paper, we outline a general comprehension-based approach to the evaluation of plan-based story generation. We describe how we specialize it for use evaluating story plans containing failed actions, and we describe the design and results of an experiment using this approach to evaluate plot lines produced by HeadSpace, a system that models the beliefs of characters and uses that model to generate plot lines containing actions that are attempted but that fail.