In this paper we present two studies supporting a plan-based model of narrative generation that reasons about both intentionality and belief. First we compare the believability of agent plans taken from the spaces of valid classical plans, intentional plans, and belief plans. We show that the plans that make the most sense to humans are those in the overlapping regions of the intentionality and belief spaces. Second, we validate the model’s approach to representing anticipation, where characters form plans that involve actions they expect other characters to take. Using a short interactive scenario we demonstrate that players not only find it believable when NPCs anticipate their actions, but sometimes actively anticipate the actions of NPCs in a way that is consistent with the model.
Inferring and Conveying Intentionality: Beyond Numerical Rewards to Logical Intentions
Shared intentionality is a critical component in developing conscious AI agents capable of collaboration, self-reflection, deliberation, and reasoning. We formulate inference of shared intentionality as an inverse reinforcement learning problem with logical reward specifications.
We show how the approach can infer task descriptions from demonstrations. We also extend our approach to actively convey intentionality. We demonstrate the approach on a simple grid-world example.
- Publication Date:
- NSF-PAR ID:
- 10119091
- Journal Name:
- AAAI Symposium on Towards Conscious AI Systems
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Goal modeling enables the elicitation of stakeholders’ intentionality in the earlier stages of a project. Often, approaches are limited by the effort required to create an initial goal model. In this paper, we investigate the problem of model merging for Tropos goal models. Specifically, we propose a formal approach to the problem of automatically merging the attributes of intentions and actors, once these elements have been matched. Additionally, recent approaches have investigated answering questions about future evolutions of stakeholders’ projects with goal models. In this work we consider both static models, as well as those with timing information, using the principles of gullibility, contradiction, and consensus. We study our implementation and validate the merge operation on a variety of models from the literature.
-
Despite efforts over the past few decades to promote diversity and foster inclusive campus climates, there is still underrepresentation of Blacks/ African Americans, Latinx/Hispanics, and Native Americans (including Native Hawaiians and Alaska Natives) within the STEM professoriate nationwide. For students who are members of these groups, the culturally isolating experience this deficit creates can weaken one's academic self-perception, and hinder performance in STEM disciplines. This paper explores the relationship between intentionality towards diversity and inclusion in faculty job postings and corresponding faculty demographics at a variety of US postsecondary institutions. The research questions we are investigating are: •In what ways are diversity and inclusion implicitly and explicitly addressed in the evaluated job postings? •Does intentionality towards diversity and inclusion in job postings vary based on the type of position advertised (i.e., tenured/tenure track versus non-tenure-track) or institution type (i.e., Basic Carnegie Classification)? Using HigherEdJobs.com, we conducted an advanced search of all open science and engineering faculty positions containing the keywords "data science", "data engineering", "data analysis", or "data analytics." Each result posted in September 2019 that advertised a full-time tenured/tenure-track or non-tenure track faculty appointment for at least one academic year at a US college or university was recorded. Allmore »
-
This project explores how engineering students understand diversity and inclusion within their engineering programs, and how these understandings are shaped by aspects of the environment in which they are situated. Our study is a component of a broader research project that is examining the seemingly intractable problems of diversity and inclusion that emerge through the converging threads of formation of professional identity and culture of engineering disciplines. In this study we utilized a qualitative analysis of interview data to explore the undergraduate students’ perceptions of diversity and inclusion within the School of Electrical and Computer Engineering (ECE) at Purdue University [1]. Our interview draws upon cultural dimensions of engineering disciplines that encourage student to reflect upon and assess diversity and inclusion efforts within ECE [2]. To interrogate students’ perceptions of diversity and inclusion, we interviewed 13 current or past undergraduate ECE students. With nearly 40 percent of the undergraduate ECE students identifying as international students, such a significant international population poses tremendous learning opportunities as well as challenges related to diversity and inclusion. Thus, formal efforts within ECE have been made to bridge cultural differences, develop intercultural competencies, and promote inclusion of internationally and domestically diverse ECE members. However, thesemore »
-
Successfully navigating the social world requires reasoning about both high-level strategic goals, such as whether to cooperate or compete, as well as the low-level actions needed to achieve those goals. While previous work in experimental game theory has examined the former and work on multi-agent systems has examined the later, there has been little work investigating behavior in environments that require simultaneous planning and inference across both levels. We develop a hierarchical model of social agency that infers the intentions of other agents, strategically decides whether to cooperate or compete with them, and then executes either a cooperative or competitive planning program. Learning occurs across both high-level strategic decisions and low-level actions leading to the emergence of social norms. We test predictions of this model in multi-agent behavioral experiments using rich video-game like environments. By grounding strategic behavior in a formal model of planning, we develop abstract notions of both cooperation and competition and shed light on the computational nature of joint intentionality.