Lewis Hammond

Lewis Hammond

Auto-generated profile, based on publicly available information

Lewis Hammond

University of Oxford

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
3 June 2024
Verified
Conference Paper
Open access
ACAlan Chan
Alan Chan
CECarson Ezell
Carson Ezell
MKMax Kaufmann
Max Kaufmann
KWKevin Wei
Kevin Wei
LHLewis Hammond
Lewis Hammond
MAMarkus Anderljung
Markus Anderljung
Increased delegation of commercial, scientific, governmental, and personal activities to AI agents—systems capable of pursuing complex goals with limited supervision—may exacerbate existing societal risks and introduce new risks. Understanding and mitigating these risks involves critically evaluating existing governance structures, revising and adapting these structures where needed, and ensuring accountability of key stakeholders. Information about where, why, how, and by whom certain AI agents are used, which we refer to as visibility, is critical to these objectives. In this paper, we assess three categories of measures to increase visibility into AI agents: agent identifiers, real-time monitoring, and activity logging. For each, we outline potential implementations that vary in intrusiveness and informativeness. We analyze how the measures apply across a spectrum of centralized through decentralized deployment contexts, accounting for various actors in the supply chain including hardware and software service providers. Finally, we discuss the implications of our measures for privacy and concentration of power. Further work into understanding the measures and mitigating their negative impacts can help to build a foundation for the governance of AI agents.

3 August 2021 in Applied Intelligence
Verified
Journal Article
Open access
PDF file
AAAlessandro Abate
Alessandro Abate
Julian GutierrezJulian Gutierrez
Julian Gutierrez
LHLewis Hammond
Lewis Hammond
PHPaul Harrenstein
Paul Harrenstein
MKMarta Kwiatkowska
Marta Kwiatkowska
MWMichael Wooldridge
Michael Wooldridge
We provide a survey of the state of the art ofrational verification: the problem of checking whether a given temporal logic formulaϕis satisfied in some or all game-theoretic equilibria of a multi-agent system – that is, whether the system will exhibit the behaviorϕrepresents under the assumption that agents within the system act rationally in pursuit of their preferences. After motivating and introducing the overall framework of rational verification, we discuss key results obtained in the past few years as well as relevant related work in logic, AI, and computer science.

16 June 2025 in Proceedings of the National Academy of Sciences
Verified
Journal Article
Open access
WBWolfram Barfuss
Wolfram Barfuss
JFJessica Flack
Jessica Flack
CGChaitanya Gokhale
Chaitanya Gokhale
LHLewis Hammond
Lewis Hammond
CHChristian Hilbe
Christian Hilbe
FSFernando P. Santos
Fernando P. Santos
Cooperation at scale is critical for achieving a sustainable future for humanity. However, achieving collective, cooperative behavior—in which intelligent actors in complex environments jointly improve their well-being—remains poorly understood. Complex systems science (CSS) provides a rich understanding of collective phenomena, the evolution of cooperation, and the institutions that can sustain both. Yet, much of the theory in this area fails to fully consider individual-level complexity and environmental context—largely for the sake of tractability and because it has not been clear how to do so rigorously. These elements are well captured in multiagent reinforcement learning (MARL), which has recently put focus on cooperative (artificial) intelligence. However, typical MARL simulations can be computationally expensive and challenging to interpret. In this perspective, we propose that bridging CSS and MARL affords new directions forward. Both fields can complement each other in their goals, methods, and scope. MARL offers CSS concrete ways to formalize cognitive processes in dynamic environments. CSS offers MARL improved qualitative insight into emergent collective phenomena. We see this approach as providing the necessary foundations for a proper science of collective, cooperative intelligence. We highlight work that is already heading in this direction and discuss concrete steps for future research.

5 April 2023 in Artificial Intelligence
Verified
Journal Article
Open access
LHLewis Hammond
Lewis Hammond
JFJames Fox
James Fox
TETom Everitt
Tom Everitt
RCRyan Carey
Ryan Carey
AAAlessandro Abate
Alessandro Abate
MWMichael Wooldridge
Michael Wooldridge

25 January 2021 in Data Mining and Knowledge Discovery
Verified
Journal Article
Open access
PDF file
LHLewis Hammond
Lewis Hammond
VBVaishak Belle
Vaishak Belle
Moral responsibility is a major concern in autonomous systems, with applications ranging from self-driving cars to kidney exchanges. Although there have been recent attempts to formalise responsibility and blame, among similar notions, the problem of learning within these formalisms has been unaddressed. From the viewpoint of such systems, the urgent questions are: (a) How can models of moral scenarios and blameworthiness be extracted and learnt automatically from data? (b) How can judgements be computed effectively and efficiently, given the split-second decision points faced by some systems? By building on constrained tractable probabilistic learning, we propose and implement a hybrid (between data-driven and rule-based methods) learning framework for inducing models of such scenarios automatically from data and reasoning tractably from them. We report on experiments that compare our system with human judgement in three illustrative domains: lung cancer staging, teamwork management, and trolley problems.

11 July 2023 in Electronic Proceedings in Theoretical Computer Science
Verified
Journal Article
Open access
PDF file
JFJames Fox
James Fox
MMMatt MacDermott
Matt MacDermott
LHLewis Hammond
Lewis Hammond
PHPaul Harrenstein
Paul Harrenstein
AAAlessandro Abate
Alessandro Abate
MWMichael Wooldridge
Michael Wooldridge
Multi-agent influence diagrams (MAIDs) are a popular game-theoretic model based on Bayesian networks. In some settings, MAIDs offer significant advantages over extensive-form game representations. Previous work on MAIDs has assumed that agents employ behavioural policies, which set independent conditional probability distributions over actions for each of their decisions. In settings with imperfect recall, however, a Nash equilibrium in behavioural policies may not exist. We overcome this by showing how to solve MAIDs with forgetful and absent-minded agents using mixed policies and two types of correlated equilibrium. We also analyse the computational complexity of key decision problems in MAIDs, and explore tractable cases. Finally, we describe applications of MAIDs to Markov games and team situations, where imperfect recall is often unavoidable.