skip to main content

Title: 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.
Authors:
;
Award ID(s):
1740079 1750009
Publication Date:
NSF-PAR ID:
10119091
Journal Name:
AAAI Symposium on Towards Conscious AI Systems
Sponsoring Org:
National Science Foundation
More Like this
  1. 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.
  2. 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 »qualifying job postings were qualitatively analyzed for active, intentional recruitment of URM candidates. Intentionality towards diversity and inclusion varied significantly across job postings. While some had no reference to diversity beyond a required one-sentence equal employment opportunity (EEO) statement, others explicitly addressed inclusion within the announcements, and still others required a standalone diversity statement as part of a complete application. The results will help to inform strategies for recruiting URM faculty in STEM disciplines, which may lead to improved opportunities to create cultures of inclusion and support for diverse students (undergraduate and graduate) and postdoctoral fellows.« less
  3. 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 »efforts have met with mixed results. Our analysis of the interview data suggests that these efforts often were not aligned with literature about how to successfully bridge culture differences in that they lacked an explicit focus on students’ understandings of diversity and inclusion, nor did they provide opportunities for students to reflect on their personal and educational experiences. In what follows, we first examine the framing of scholarship about diversity and inclusion within engineering and then draw upon literature using Kolb’s experiential learning models to illuminate the transformational nature that reflection plays within establishing ways of viewing complex social problems. With this combination and reimagining of reflection as a pathway to more deeply understanding diversity and inclusion, we describe our research methods, data analysis, and the findings from our qualitative analysis. Finally, we conclude with a discussion of the tensions pertaining to difference and sameness that emerged through our analysis. Namely, formal efforts within ECE required both scaffolding and intentionality. Without proper facilitation, the central role that diversity and inclusion plays within professional formation appeared forced, created more cultural isolation, or students ignored these efforts altogether to complete assignments. We conclude by offering both theoretical and pragmatic implications for engineering curriculum.« less
  4. 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.
  5. Abstract

    In response to the growing computational intensity of the healthcare industry, biomedical engineering (BME) undergraduate education is placing increased emphasis on computation. The presence of substantial gender disparities in many computationally intensive disciplines suggests that the adoption of computational instruction approaches that lack intentionality may exacerbate gender disparities. Educational research suggests that the development of an engineering and computational identity is one factor that can support students’ decisions to enter and persist in an engineering major. Discipline-based identity research is used as a lens to understand retention and persistence of students in engineering. Our specific purpose is to apply discipline-based identity research to define and explore the computational identities of undergraduate engineering students who engage in computational environments. This work will inform future studies regarding retention and persistence of students who engage in computational courses. Twenty-eight undergraduate engineering students (20 women, 8 men) from three engineering majors (biomedical engineering, agricultural engineering, and biological engineering) participated in semi-structured interviews. The students discussed their experiences in a computationally-intensive thermodynamics course offered jointly by the Biomedical Engineering and Agricultural & Biological Engineering departments. The transcribed interviews were analyzed through thematic coding. The gender stereotypes associated with computer programming also come part andmore »parcel with computer programming, possibly threatening a student's sense of belonging in engineering. The majority of the participants reported that their computational identity was “in the making.” Students’ responses also suggested that their engineering identity and their computational identity were in congruence, while some incongruence is found between their engineering identity and a creative identity as well as between computational identity and perceived feminine norms. Responses also indicate that students associate specific skills with having a computational identity. This study's findings present an emergent thematic definition of a computational person constructed from student perceptions and experiences. Instructors can support students’ nascent computational identities through intentional mitigation of the gender stereotypes and biases, and by framing assignments to focus on developing specific skills associated with the computational modeling processes.

    « less