Leveraging efficient planning and lightweight agent definition: a novel path towards emergent narrative


Loading...

Date

2020-10

Publication Type

Conference Paper

ETH Bibliography

yes

Citations

Altmetric

Data

Abstract

Emergent narrative has the ability to unlock the true potential of interactive media, moving beyond pre-scripted, fixed story- lines. Existing implementations of emergent narrative achieve their results through complex rule systems and agent representations, which entail high authoring workload that limit the feasible scope of storyworlds. In this paper, we propose an approach that instead aims at leveraging efficient planning to achieve similar results, using Monte Carlo Tree Search and efficient data structures. This allows for abstraction and modularization of agent behavior, and endows agents with a theory of mind by letting them plan for each other. This greatly simplifies agent definition and removes the need to explicitly encode intentions. We show that competitive, collaborative and sustainable behaviors emerge in our system, without the explicit definition of such behaviors. Based on these preliminary results, we discuss necessary steps to turn our approach into an applicable emergent narrative system.

Publication status

published

External links

Editor

Book title

Journal / series

Volume

Pages / Article No.

Publisher

ETH Zurich, Game Technology Center (GTC)

Event

12th Intelligent Narrative Technolgies Workshop, held with the AIIDE Conference (INT10 2020)

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

emergent storytelling; multi-agent simulation; theory of mind; Monte Carlo Tree Search (MCTS); artificial intelligence; action planning

Organisational unit

08698 - Game Technology Center (GTC)

Notes

Conference lecture held on October 19, 2020. Due to the Coronavirus (COVID-19) the conference was conducted virtually.

Funding

Related publications and datasets