Liz Sonenberg

AAMAS Conference 2024 Conference Paper

Agents and Humans: Trajectories and Perspectives

• Liz Sonenberg

The AAMAS conference was established in 2002 as the merger of three highly successful conferences: AA (the International Conference on Autonomous Agents), ICMAS (the International Conference on Multiagent Systems) and ATAL (the International Workshop on Agent Theories, Architectures, and Languages). In this talk I draw on my own experiences and that of others in investigating human-agent collectives. I reflect on aspects of the trajectory of research topics in the AAMAS community over the past 20+ years, and on selected challenges for human-centred AI.

ECAI Conference 2024 Conference Paper

Towards the New XAI: A Hypothesis-Driven Approach to Decision Support Using Evidence

• Thao Le 0002
• Tim Miller 0001
• Liz Sonenberg
• Ronal Singh

Prior research on AI-assisted human decision-making has explored several different explainable AI (XAI) approaches. A recent paper has proposed a paradigm shift calling for hypothesis-driven XAI through a conceptual framework called evaluative AI that gives people evidence that supports or refutes hypotheses without necessarily giving a decision-aid recommendation. In this paper, we describe and evaluate an approach for hypothesis-driven XAI based on the Weight of Evidence (WoE) framework, which generates both positive and negative evidence for a given hypothesis. Through human behavioural experiments, we show that our hypothesis-driven approach increases decision accuracy and reduces reliance compared to a recommendation-driven approach and an AI-explanation-only baseline, but with a small increase in under-reliance compared to the recommendation-driven approach. Further, we show that participants used our hypothesis-driven approach in a materially different way to the two baselines.

AAAI Conference 2023 Conference Paper

Explaining Model Confidence Using Counterfactuals

• Thao Le
• Tim Miller
• Ronal Singh
• Liz Sonenberg

Displaying confidence scores in human-AI interaction has been shown to help build trust between humans and AI systems. However, most existing research uses only the confidence score as a form of communication. As confidence scores are just another model output, users may want to understand why the algorithm is confident to determine whether to accept the confidence score. In this paper, we show that counterfactual explanations of confidence scores help study participants to better understand and better trust a machine learning model's prediction. We present two methods for understanding model confidence using counterfactual explanation: (1) based on counterfactual examples; and (2) based on visualisation of the counterfactual space. Both increase understanding and trust for study participants over a baseline of no explanation, but qualitative results show that they are used quite differently, leading to recommendations of when to use each one and directions of designing better explanations.

AIJ Journal 2023 Journal Article

The effects of explanations on automation bias

• Mor Vered
• Tali Livni
• Piers Douglas Lionel Howe
• Tim Miller
• Liz Sonenberg

In this paper we explore the effect of explanations on reducing errors in the human decision making process caused by placing excessive reliance on automated decision support systems. We develop and implement different forms of explanations based on cognitive principles and evaluate their effect over two different domains: our new version of the Coloured Trails game, and over a simulated radiological task. We found that explanations did not reduce this aspect of automation bias and sometimes increased it. However, they reduced completion time and often increased user decision accuracy, despite not altering the perceived task load. Overall, explanations were beneficial though the benefits were highly context dependent. This work contributes to the complex interplay between automation bias, performance and explanations.

AIJ Journal 2022 Journal Article

Efficient multi-agent epistemic planning: Teaching planners about nested belief

• Christian Muise
• Vaishak Belle
• Paolo Felli
• Sheila McIlraith
• Tim Miller
• Adrian R. Pearce
• Liz Sonenberg

Many AI applications involve the interaction of multiple autonomous agents, requiring those agents to reason about their own beliefs, as well as those of other agents. However, planning involving nested beliefs is known to be computationally challenging. In this work, we address the task of synthesizing plans that necessitate reasoning about the beliefs of other agents. We plan from the perspective of a single agent with the potential for goals and actions that involve nested beliefs, non-homogeneous agents, co-present observations, and the ability for one agent to reason as if it were another. We formally characterize our notion of planning with nested belief, and subsequently demonstrate how to automatically convert such problems into problems that appeal to classical planning technology for solving efficiently. Our approach represents an important step towards applying the well-established field of automated planning to the challenging task of planning involving nested beliefs of multiple agents.

AIJ Journal 2020 Journal Article

Combining gaze and AI planning for online human intention recognition

• Ronal Singh
• Tim Miller
• Joshua Newn
• Eduardo Velloso
• Frank Vetere
• Liz Sonenberg

Intention recognition is the process of using behavioural cues, such as deliberative actions, eye gaze, and gestures, to infer an agent's goals or future behaviour. In artificial intelligence, one approach for intention recognition is to use a model of possible behaviour to rate intentions as more likely if they are a better ‘fit’ to actions observed so far. In this paper, we draw from literature linking gaze and visual attention, and we propose a novel model of online human intention recognition that combines gaze and model-based AI planning to build probability distributions over a set of possible intentions. In human-behavioural experiments ( n = 40 ) involving a multi-player board game, we demonstrate that adding gaze-based priors to model-based intention recognition improved the accuracy of intention recognition by 22% ( p < 0. 05 ), determined those intentions ≈90 seconds earlier ( p < 0. 05 ), and at no additional computational cost. We also demonstrate that, when evaluated in the presence of semi-rational or deceptive gaze behaviours, the proposed model is significantly more accurate (9% improvement) ( p < 0. 05 ) compared to a model-based or gaze only approaches. Our results indicate that the proposed model could be used to design novel human-agent interactions in cases when we are unsure whether a person is honest, deceitful, or semi-rational.

AAAI Conference 2020 Conference Paper

Explainable Reinforcement Learning through a Causal Lens

• Prashan Madumal
• Tim Miller
• Liz Sonenberg
• Frank Vetere

Prominent theories in cognitive science propose that humans understand and represent the knowledge of the world through causal relationships. In making sense of the world, we build causal models in our mind to encode cause-effect relations of events and use these to explain why new events happen by referring to counterfactuals — things that did not happen. In this paper, we use causal models to derive causal explanations of the behaviour of model-free reinforcement learning agents. We present an approach that learns a structural causal model during reinforcement learning and encodes causal relationships between variables of interest. This model is then used to generate explanations of behaviour based on counterfactual analysis of the causal model. We computationally evaluate the model in 6 domains and measure performance and task prediction accuracy. We report on a study with 120 participants who observe agents playing a real-time strategy game (Starcraft II) and then receive explanations of the agents' behaviour. We investigate: 1) participants' understanding gained by explanations through task prediction; 2) explanation satisfaction and 3) trust. Our results show that causal model explanations perform better on these measures compared to two other baseline explanation models.

AAMAS Conference 2019 Conference Paper

A Grounded Interaction Protocol for Explainable Artificial Intelligence

• Prashan Madumal
• Tim Miller
• Liz Sonenberg
• Frank Vetere

Explainable Artificial Intelligence (XAI) systems need to include an explanation model to communicate the internal decisions, behaviours and actions to the interacting humans. Successful explanation involves both cognitive and social processes. In this paper we focus on the challenge of meaningful interaction between an explainer and an explainee and investigate the structural aspects of an interactive explanation to propose an interaction protocol. We follow a bottom-up approach to derive the model by analysing transcripts of different explanation dialogue types with 398 explanation dialogues. We use grounded theory to code and identify key components of an explanation dialogue. We formalize the model using the agent dialogue framework (ADF) as a new dialogue type and then evaluate it in a human-agent interaction study with 101 dialogues from 14 participants. Our results show that the proposed model can closely follow the explanation dialogues of human-agent conversations.

AAMAS Conference 2018 Conference Paper

Combining Planning with Gaze for Online Human Intention Recognition

• Ronal Singh
• Tim Miller
• Joshua Newn
• Liz Sonenberg
• Eduardo Velloso
• Frank Vetere

Intention recognition is the process of using behavioural cues to infer an agent’s goals or future behaviour. People use many behavioural cues to infer others’ intentions, such as deliberative actions, facial expressions, eye gaze, and gestures. In artificial intelligence, two approaches for intention recognition, among others, are gaze-based and model-based intention recognition. Approaches in the former class use gaze to determine which parts of a space a person looks at more often to infer a person’s intention. Approaches in the latter use models of possible future behaviour to rate intentions as more likely if they are a better ‘fit’ to observed actions. In this paper, we propose a novel model of human intention recognition that combines gaze and model-based approaches for online human intention recognition. Gaze data is used to build probability distributions over a set of possible intentions, which are then used as priors in a model-based intention recognition algorithm. In humanbehavioural experiments (n = 20) involving a multi-player board game, we found that adding gaze-based priors to model-based intention recognition more accurately determined intentions (p < 0. 01), determined those intentions earlier (p < 0. 01), and at no additional cost; all compared to a model-based-only approach.

JAIR Journal 2017 Journal Article

Logics of Common Ground

• Tim Miller
• Jens Pfau
• Liz Sonenberg
• Yoshihisa Kashima

According to Clark's seminal work on common ground and grounding, participants collaborating in a joint activity rely on their shared information, known as common ground, to perform that activity successfully, and continually align and augment this information during their collaboration. Similarly, teams of human and artificial agents require common ground to successfully participate in joint activities. Indeed, without appropriate information being shared, using agent autonomy to reduce the workload on humans may actually increase workload as the humans seek to understand why the agents are behaving as they are. While many researchers have identified the importance of common ground in artificial intelligence, there is no precise definition of common ground on which to build the foundational aspects of multi-agent collaboration. In this paper, building on previously-defined modal logics of belief, we present logic definitions for four different types of common ground. We define modal logics for three existing notions of common ground and introduce a new notion of common ground, called salient common ground. Salient common ground captures the common ground of a group participating in an activity and is based on the common ground that arises from that activity as well as on the common ground they shared prior to the activity. We show that the four definitions share some properties, and our analysis suggests possible refinements of the existing informal and semi-formal definitions.

AAAI Conference 2016 Conference Paper

Knowing Whether’ in Proper Epistemic Knowledge Bases

• Tim Miller
• Paolo Felli
• Christian Muise
• Adrian Pearce
• Liz Sonenberg

Proper epistemic knowledge bases (PEKBs) are syntactic knowledge bases that use multi-agent epistemic logic to represent nested multi-agent knowledge and belief. PEKBs have certain syntactic restrictions that lead to desirable computational properties; primarily, a PEKB is a conjunction of modal literals, and therefore contains no disjunction. Sound entailment can be checked in polynomial time, and is complete for a large set of arbitrary formulae in logics Kn and KDn. In this paper, we extend PEKBs to deal with a restricted form of disjunction: ‘knowing whether’. An agent i knows whether ϕ iff agent i knows ϕ or knows ¬ϕ; that is, iϕ ∨ i¬ϕ. In our experience, the ability to represent that an agent knows whether something holds is useful in many multi-agent domains. We represent knowing whether with a modal operator, Δi, and present sound polynomial-time entailment algorithms on PEKBs with Δi in Kn and KDn, but which are complete for a smaller class of queries than standard PEKBs.

IJCAI Conference 2016 Conference Paper

Planning for a Single Agent in a Multi-Agent Environment Using FOND

• Christian Muise
• Paolo Felli
• Tim Miller
• Adrian R. Pearce
• Liz Sonenberg

Single-agent planning in a multi-agent environment is challenging because the actions of other agents can affect our ability to achieve a goal. From a given agent's perspective, actions of others can be viewed as non-deterministic outcomes of that agent's actions. While simple conceptually, this interpretation of planning in a multi-agent environment as non-deterministic planning remains challenging, not only due to the non-determinism resulting from others' actions, but because it is not clear how to compactly model the possible actions of others in the environment. In this paper, we cast the problem of planning in a multi-agent environment as one of Fully-Observable Non-Deterministic (FOND) planning. We extend a non-deterministic planner to plan in a multi-agent setting, allowing non-deterministic planning technology to solve a new class of planning problems. To improve the efficiency in domains too large for solving optimally, we propose a technique to use the goals and possible actions of other agents to focus the search on a set of plausible actions. We evaluate our approach on existing and new multi-agent benchmarks, demonstrating that modelling the other agents' goals improves the quality of the resulting solutions.

IJCAI Conference 2015 Conference Paper

Computing Social Behaviours Using Agent Models

• Paolo Felli
• Tim Miller
• Christian Muise
• Adrian R. Pearce
• Liz Sonenberg

Agents can be thought of as following a social behaviour, depending on the context in which they are interacting. We devise a computationally grounded mechanism to represent and reason about others in social terms, reflecting the local perspective of an agent (first-person view), to support both stereotypical and empathetic reasoning. We use a hierarchy of agent models to discriminate which behaviours of others are plausible, and decide which behaviour for ourselves is socially acceptable, i. e. conforms to the social context. To this aim, we investigate the implications of considering agents capable of various degrees of theory of mind, and discuss a scenario showing how this affects behaviour.

AAAI Conference 2015 Conference Paper

Planning Over Multi-Agent Epistemic States: A Classical Planning Approach

• Christian Muise
• Vaishak Belle
• Paolo Felli
• Sheila McIlraith
• Tim Miller
• Adrian Pearce
• Liz Sonenberg

Many AI applications involve the interaction of multiple autonomous agents, requiring those agents to reason about their own beliefs, as well as those of other agents. However, planning involving nested beliefs is known to be computationally challenging. In this work, we address the task of synthesizing plans that necessitate reasoning about the beliefs of other agents. We plan from the perspective of a single agent with the potential for goals and actions that involve nested beliefs, non-homogeneous agents, co-present observations, and the ability for one agent to reason as if it were another. We formally characterize our notion of planning with nested belief, and subsequently demonstrate how to automatically convert such problems into problems that appeal to classical planning technology. Our approach represents an important first step towards applying the well-established field of automated planning to the challenging task of planning involving nested beliefs of multiple agents.

JAAMAS Journal 2010 Journal Article

An empirical study of interest-based negotiation

• Philippe Pasquier
• Ramon Hollands
• Liz Sonenberg

Abstract While argumentation-based negotiation has been accepted as a promising alternative to game-theoretic or heuristic-based negotiation, no evidence has been provided to confirm this theoretical advantage. We propose a model of bilateral negotiation extending a simple monotonic concession protocol by allowing the agents to exchange information about their underlying interests and possible alternatives to achieve them during the negotiation. We present an empirical study that demonstrates (through simulation) the advantages of this interest-based negotiation approach over the more classic monotonic concession approach to negotiation.

AAMAS Conference 2010 Conference Paper

Wishful Thinking In Effective Decision Making

• Jonathan Ito
• David Pynadath
• Liz Sonenberg
• Stacy Marsella

Creating agents that act reasonably in uncertain environments is a primary goal of agent-based research. In this workwe explore the theory that wishful thinking can be an ective strategy in uncertain and competitive decision scenarios. Specifically, we present the constraints necessary for wishful thinking to outperform Expected Utility Maximizationand take instances of popular games from Game-Theoreticliterature showing how they relate to our constraints andwhether they can benefit from wishful-thinking.

JAAMAS Journal 2008 Journal Article

Intentional learning agent architecture

• Budhitama Subagdja
• Liz Sonenberg
• Iyad Rahwan

Abstract Dealing with changing situations is a major issue in building agent systems. When the time is limited, knowledge is unreliable, and resources are scarce, the issue becomes more challenging. The BDI (Belief-Desire-Intention) agent architecture provides a model for building agents that addresses that issue. The model can be used to build intentional agents that are able to reason based on explicit mental attitudes, while behaving reactively in changing circumstances. However, despite the reactive and deliberative features, a classical BDI agent is not capable of learning. Plans as recipes that guide the activities of the agent are assumed to be static. In this paper, an architecture for an intentional learning agent is presented. The architecture is an extension of the BDI architecture in which the learning process is explicitly described as plans. Learning plans are meta-level plans which allow the agent to introspectively monitor its mental states and update other plans at run time. In order to acquire the intricate structure of a plan, a process pattern called manipulative abduction is encoded as a learning plan. This work advances the state of the art by combining the strengths of learning and BDI agent frameworks in a rich language for describing deliberation processes and reactive execution. It enables domain experts to specify learning processes and strategies explicitly, while allowing the agent to benefit from procedural domain knowledge expressed in plans.

AAAI Conference 2007 Conference Paper

On the Benefits of Exploiting Underlying Goals in Argument-based Negotiation

• Iyad Rahwan
• Liz Sonenberg

Interest-based negotiation (IBN) is a form of negotiation in which agents exchange information about their underlying goals, with a view to improving the likelihood and quality of a deal. While this intuition has been stated informally in much previous literature, there is no formal analysis of the types of deals that can be reached through IBN and how they differ from those reachable using (classical) alternating offer bargaining. This paper bridges this gap by providing a formal framework for analysing the outcomes of IBN dialogues, and begins by analysing a specific IBN protocol.

JAAMAS Journal 2005 Journal Article

A Real-Time Negotiation Model and A Multi-Agent Sensor Network Implementation

• Carles Sierra
• Liz Sonenberg

KER Journal 2003 Journal Article

Argumentation-based negotiation

• Iyad Rahwan
• Sarvapali D. Ramchurn
• Nicholas R. Jennings
• Peter McBurney
• Simon Parsons
• Liz Sonenberg

Negotiation is essential in settings where autonomous agents have conflicting interests and a desire to cooperate. For this reason, mechanisms in which agents exchange potential agreements according to various rules of interaction have become very popular in recent years as evident, for example, in the auction and mechanism design community. However, a growing body of research is now emerging which points out limitations in such mechanisms and advocates the idea that agents can increase the likelihood and quality of an agreement by exchanging arguments which influence each others' states. This community further argues that argument exchange is sometimes essential when various assumptions about agent rationality cannot be satisfied. To this end, in this article, we identify the main research motivations and ambitions behind work in the field. We then provide a conceptual framework through which we outline the core elements and features required by agents engaged in argumentation-based negotiation, as well as the environment that hosts these agents. For each of these elements, we survey and evaluate existing proposed techniques in the literature and highlight the major challenges that need to be addressed if argument-based negotiation research is to reach its full potential.

AAMAS Conference 2003 Conference Paper

Towards Interest-Based Negotiation

• Iyad Rahwan
• Liz Sonenberg
• Frank Dignum

UAI Conference 2001 Conference Paper

A Case Study in Knowledge Discovery and Elicitation in an Intelligent Tutoring Application

• Ann E. Nicholson
• Tal Boneh
• Tim A. Wilkin 0001
• Kaye Stacey
• Liz Sonenberg
• Vicki Steinle

Most successful Bayesian network (BN) applications to datehave been built through knowledge elicitation from experts.This is difficult and time consuming, which has lead to recentinterest in automated methods for learning BNs from data. We present a case study in the construction of a BN in anintelligent tutoring application, specifically decimal misconceptions. Wedescribe the BN construction using expert elicitation and then investigate how certainexisting automated knowledge discovery methods might support the BN knowledge engineering process.