Author name cluster

Silvia Tulli

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

5 papers

1 author row

AAAI Conference 2026 Conference Paper

Explanations for Sequential Decision-Making – an Overview

Hendrik Baier
Mark T. Keane
Sarath Sreedharan
Silvia Tulli
Abhinav Verma

In this paper, we highlight the field of explainable sequential decision making. We discuss how the problem of explaining sequential decisions gives rise to problems and challenges that are absent from scenarios that focus on explaining single-shot decision making. We provide a short survey of some of the more prominent subareas within explainable sequential decision-making and their unique focuses and blind spots. Here, we argue that we need to go beyond simply focusing on individual subareas like explainable planning, reinforcement learning, or robotics, and move towards studying and tackling the more general problem of explainable sequential decision-making. Such a holistic approach will not only allow us to identify previously ignored problems, but also provide us with the ability to transfer ideas and intuitions from one subarea of explainable sequential decision-making to another. We end the paper with a discussion on future directions and some of the most pressing open questions.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Inferring Implicit Goals Across Differing Task Models

Silvia Tulli
Stylianos Loukas Vasileiou
Mohamed CHETOUANI
Sarath Sreedharan

One of the significant challenges to generating value-aligned behavior is to not only account for the specified user objectives but also any implicit or unspecified user requirements. The existence of such implicit requirements could be particularly common in settings where the user's understanding of the task model may differ from the agent's estimate of the model. Under this scenario, the user may incorrectly expect some agent behavior to be inevitable or guaranteed. This paper addresses such expectation mismatch in the presence of differing models by capturing the possibility of unspecified user subgoal in the context of a task captured as a Markov Decision Process (MDP) and querying for it as required. Our method identifies bottleneck states and uses them as candidates for potential implicit subgoals. We then introduce a querying strategy that will generate the minimal number of queries required to identify a policy guaranteed to achieve the underlying goal. Our empirical evaluations demonstrate the effectiveness of our approach in inferring and achieving unstated goals across various tasks.

PDF Details DOI

HAXP Workshop 2024 Workshop Paper

Human-Modeling in Sequential Decision-Making: An Analysis through the Lens of Human-Aware AI

Silvia Tulli
Stylianos Loukas Vasileiou
Sarath Sreedharan

"Human-aware'' has become a popular keyword used to describe a particular class of AI systems that are designed to work and interact with humans. While there exists a surprising level of consistency among the works that use the label human-aware, the term itself mostly remains poorly understood. In this work, we retroactively try to provide an account of what constitutes a human-aware AI system. We see that human-aware AI is a design oriented paradigm, one that focuses on the need for modeling the humans it may interact with. Additionally, we see that this paradigm offers us intuitive dimensions to understand and categorize the kinds of interactions these systems might have with humans. We show the pedagogical value of these dimensions by using them as a tool to understand and review the current landscape of work related to human-AI systems that purport some form of human modeling. To fit the scope of a workshop paper, we specifically narrowed our review to papers that deal with sequential decision-making and were published in a major AI conference in the last three years. Our analysis helps identify the space of potential research problems that are currently being overlooked. We perform additional analysis on the degree to which these works make explicit reference to results from social science and whether they actually perform user-studies to validate their systems. We also provide an accounting of the various AI methods used by these works. Our analysis helps identify the space of potential research problems that are currently being overlooked. We perform additional analysis on the degree to which these works make explicit reference to results from social science and whether they actually perform user-studies to validate their systems. We also provide an accounting of the various AI methods used by these works.

PDF

AAAI Conference 2020 Short Paper

Explainability in Autonomous Pedagogical Agents

Silvia Tulli

The research presented herein addresses the topic of explainability in autonomous pedagogical agents. We will be investigating possible ways to explain the decision-making process of such pedagogical agents (which can be embodied as robots) with a focus on the effect of these explanations in concrete learning scenarios for children. The hypothesis is that the agents' explanations about their decision making will support mutual modeling and a better understanding of the learning tasks and how learners perceive them. The objective is to develop a computational model that will allow agents to express internal states and actions and adapt to the human expectations of cooperative behavior accordingly. In addition, we would like to provide a comprehensive taxonomy of both the desiderata and methods in the explainable AI research applied to children's learning scenarios.

PDF Details

AAMAS Conference 2019 Conference Paper

For The Record - A Public Goods Game For Exploring Human-Robot Collaboration

Filipa Correia
Samuel Mascarenhas
Samuel Gomes
Silvia Tulli
Fernando P. Santos
Francisco C. Santos
Rui Prada
Francisco S. Melo

For The Record is a digital game that involves a social dilemma between a mixed team of humans and agents. Inspired by the standard public goods games, the collective goal is accessible to all team members, independently of their individual contributions. As a result, each player faces in each round the decision between cooperating with the team and defecting to obtain an individual benefit. The digital game itself allows exploring the complexity of human cooperation when teaming with agents. Moreover, playing it on a touch screen creates an additional opportunity to explore these interactions when teaming with social robots.

PDF