Timothy J. Norman

AAMAS Conference 2025 Conference Paper

HAVA: Hybrid Approach to Value-Alignment through Reward Weighing for Reinforcement Learning

• Kryspin Varys
• Federico Cerutti
• Adam Sobey
• Timothy J. Norman

Our society is governed by a set of norms which together bring about the values we cherish such as safety, fairness or trustworthiness. The goal of value alignment is to create agents that not only do their tasks but through their behaviours also promote these values. Many of the norms are written as laws or rules (legal / safety norms) but even more remain unwritten (social norms). Furthermore, the techniques used to represent these norms also differ. Safety / legal norms are often represented explicitly, for example, in some logical language while social norms are typically learned and remain hidden in the parameter space of a neural network. There is a lack of approaches in the literature that could combine these various norm representations into a single algorithm. We propose a novel method that integrates these norms into the reinforcement learning process. Our method monitors the agent’s compliance with the given norms and summarizes it in a quantity we call the agent’s reputation. This quantity is used to weigh the received rewards to motivate the agent to become value aligned. We carry out a two experiments including a continuous state space traffic problem to demonstrate the importance of the written and unwritten norms and show how our method can find the value aligned policies. Furthermore, we carry out ablations to demonstrate why it is better to combine these two groups of norms rather than using either separately.

AAAI Conference 2025 Conference Paper

Optimising Spatial Teamwork Under Uncertainty

• Gregory Everett
• Ryan J. Beal
• Tim Matthews
• Timothy J. Norman
• Sarvapali D. Ramchurn

We introduce a novel method for assessing agent teamwork based on their spatial coordination. Our approach models the influence of spatial proximity on team formation and sustained spatial dominance over adversaries using a Multi-agent Markov Decision Process. We develop an algorithm to derive efficient teamwork strategies by combining Monte Carlo Tree Search and linear programming. When applied to team defence in football (soccer) using real-world data, our approach reduces opponent threat by 21%, outperforming optimised individual behaviour by 6%. Additionally, our model enhances the predictive accuracy of future attack locations and provides deeper insights compared to existing teamwork models that do not explicitly consider the spatial dynamics of teamwork.

AAMAS Conference 2024 Conference Paper

Combinatorial Client-Master Multiagent Deep Reinforcement Learning for Task Offloading in Mobile Edge Computing

• Tesfay Zemuy Gebrekidan
• Sebastian Stein
• Timothy J. Norman

Deep reinforcement learning (DRL) is gaining popularity in taskoffloading problems because it can adapt to dynamic changes and minimize online computational complexity. However, the various types of continuous and discrete resource constraints on user devices (UDs) and mobile edge computing (MEC) servers pose challenges to the design of an efficient DRL-based task-offloading strategy. Existing DRL-based task-offloading algorithms focus on the constraints of the UDs, assuming the availability of enough storage resources on the server. Moreover, existing multiagent DRL (MADRL)–based task-offloading algorithms are homogeneous agents and consider homogeneous constraints as a penalty in their reward function. In this work, we propose a novel combinatorial client-master MADRL (CCM_MADRL) algorithm for task offloading in mobile edge computing (CCM_MADRL_MEC) that allows UDs to decide their resource requirements and the server to make a combinatorial decision based on the UDs’ requirements. CCM_MADRL_MEC is the first MADRL approach in task offloading to consider server storage capacity in addition to the constraints of the UDs. By taking advantage of the combinatorial action selection, CCM_MADRL_MEC has shown superior convergence over existing benchmark and heuristic algorithms.

AAMAS Conference 2024 Conference Paper

Deep Reinforcement Learning with Coalition Action Selection for Online Combinatorial Resource Allocation with Arbitrary Action Space

• Tesfay Zemuy Gebrekidan
• Sebastian Stein
• Timothy J. Norman

Current DRL algorithms typically assume a fixed number of possible actions and sequentially select one action at a time, making them inefficient for resource allocation problems with arbitrarily large action spaces. Sequential action selection requires updating the state for every action selected, which increases the depth of the decision, the state space, the uncertainty, and the number of executions. This affects the convergence of the algorithm and slows the execution speed. Additionally, current DRL algorithms are not efficient for online resource allocation problems with an arbitrary number of task arrivals per time step because they assume a fixed number of actions. To address these challenges, we propose a novel coalition action selection approach that enables the DRL algorithm to simultaneously select a coalition of an arbitrary number of actions from a set with an arbitrary number of possible actions. By making simultaneous decisions at each time step, coalition action selection avoids the computational cost and large state space caused by the sequential decision that updates the state multiple times. We evaluate the performance and complexity of coalition action selection and sequential action selection approaches using an online combinatorial resource allocation problem. The results demonstrate that the coalition action selection approach retains close performance to the offline optimal for various online traffic demand arrival rates of the online combinatorial resource allocation problem, while the performance of the sequential action selection approach decreases as the size of the problem increases. The experiments also demonstrate that coalition action selection has much lower computational complexity than sequential action selection.

ECAI Conference 2024 Conference Paper

Explaining an Agent's Future Beliefs Through Temporally Decomposing Future Reward Estimators

• Mark Towers
• Yali Du 0001
• Christopher T. Freeman
• Timothy J. Norman

Future reward estimation is a core component of reinforcement learning agents; i. e. , Q-value and state-value functions, predicting an agent’s sum of future rewards. Their scalar output, however, obfuscates when or what individual future rewards an agent may expect to receive. We address this by modifying an agent’s future reward estimator to predict their next N expected rewards, referred to as Temporal Reward Decomposition (TRD). This unlocks novel explanations of agent behaviour. Through TRD we can: estimate when an agent may expect to receive a reward, the value of the reward and the agent’s confidence in receiving it; measure an input feature’s temporal importance to the agent’s action decisions; and predict the influence of different actions on future rewards. Furthermore, we show that DQN agents trained on Atari environments can be efficiently retrained to incorporate TRD with minimal impact on performance.

NeurIPS Conference 2024 Conference Paper

Speaking Your Language: Spatial Relationships in Interpretable Emergent Communication

• Olaf Lipinski
• Adam J. Sobey
• Federico Cerutti
• Timothy J. Norman

Effective communication requires the ability to refer to specific parts of an observation in relation to others. While emergent communication literature shows success in developing various language properties, no research has shown the emergence of such positional references. This paper demonstrates how agents can communicate about spatial relationships within their observations. The results indicate that agents can develop a language capable of expressing the relationships between parts of their observation, achieving over 90% accuracy when trained in a referential game which requires such communication. Using a collocation measure, we demonstrate how the agents create such references. This analysis suggests that agents use a mixture of non-compositional and compositional messages to convey spatial relationships. We also show that the emergent language is interpretable by humans. The translation accuracy is tested by communicating with the receiver agent, where the receiver achieves over 78% accuracy using parts of this lexicon, confirming that the interpretation of the emergent language was successful.

AAAI Conference 2024 Conference Paper

TAPE: Leveraging Agent Topology for Cooperative Multi-Agent Policy Gradient

• Xingzhou Lou
• Junge Zhang
• Timothy J. Norman
• Kaiqi Huang
• Yali Du

Multi-Agent Policy Gradient (MAPG) has made significant progress in recent years. However, centralized critics in state-of-the-art MAPG methods still face the centralized-decentralized mismatch (CDM) issue, which means sub-optimal actions by some agents will affect other agent's policy learning. While using individual critics for policy updates can avoid this issue, they severely limit cooperation among agents. To address this issue, we propose an agent topology framework, which decides whether other agents should be considered in policy gradient and achieves compromise between facilitating cooperation and alleviating the CDM issue. The agent topology allows agents to use coalition utility as learning objective instead of global utility by centralized critics or local utility by individual critics. To constitute the agent topology, various models are studied. We propose Topology-based multi-Agent Policy gradiEnt (TAPE) for both stochastic and deterministic MAPG methods. We prove the policy improvement theorem for stochastic TAPE and give a theoretical explanation for the improved cooperation among agents. Experiment results on several benchmarks show the agent topology is able to facilitate agent cooperation and alleviate CDM issue respectively to improve performance of TAPE. Finally, multiple ablation studies and a heuristic graph search algorithm are devised to show the efficacy of the agent topology.

AAMAS Conference 2023 Conference Paper

Inferring Player Location in Sports Matches: Multi-Agent Spatial Imputation from Limited Observations

• Gregory Everett
• Ryan J. Beal
• Tim Matthews
• Joseph Early
• Timothy J. Norman
• Sarvapali D. Ramchurn

Understanding agent behaviour in Multi-Agent Systems (MAS) is an important problem in domains such as autonomous driving, disaster response, and sports analytics. Existing MAS problems typically use uniform timesteps with observations for all agents. In this work, we analyse the problem of agent location imputation, specifically posed in environments with non-uniform timesteps and limited agent observability (∼95% missing values). Our approach uses Long Short-Term Memory and Graph Neural Network components to learn temporal and inter-agent patterns to predict the location of all agents at every timestep. We apply this to the domain of football (soccer) by imputing the location of all players in a game from sparse event data (e. g. , shots and passes). Our model estimates player locations to within ∼6. 9m; a ∼62% reduction in error from the best performing baseline. This approach facilitates downstream analysis tasks such as player physical metrics, player coverage, and team pitch control. Existing solutions to these tasks often require optical tracking data, which is expensive to obtain and only available to elite clubs. By imputing player locations from easy to obtain event data, we increase the accessibility of downstream tasks.

AAMAS Conference 2023 Conference Paper

MADDM: Multi-Advisor Dynamic Binary Decision-Making by Maximizing the Utility

• Zhaori Guo
• Timothy J. Norman
• Enrico H. Gerding

Being able to infer ground truth from the responses of multiple imperfect advisors is a problem of crucial importance in many decision-making applications, such as lending, trading, investment, and crowd-sourcing. In practice, however, gathering answers from a set of advisors has a cost. Therefore, finding an advisor selection strategy that retrieves a reliable answer and maximizes the overall utility is a challenging problem. To address this problem, we propose a novel strategy for optimally selecting a set of advisers in a sequential binary decision-making setting, where multiple decisions need to be made over time. Crucially, we assume no access to ground truth and no prior knowledge about the reliability of advisers. Specifically, our approach considers how to simultaneously (1) select advisors by balancing the advisors’ costs and the value of making correct decisions, (2) learn the trustworthiness of advisers dynamically without prior information by asking multiple advisers, and (3) make optimal decisions without access to the ground truth, improving this over time. We evaluate our algorithm through several numerical experiments. The results show that our approach outperforms two other methods that combine state-of-the-art models.

AAMAS Conference 2022 Conference Paper

How to Train Your Agent: Active Learning from Human Preferences and Justifications in Safety-critical Environments

• Ilias Kazantzidis
• Timothy J. Norman
• Yali Du
• Christopher T. Freeman

Training reinforcement learning agents in real-world environments is costly, particularly for safety-critical applications. Human input can enable an agent to learn a good policy while avoiding unsafe actions, but at the cost of bothering the human with repeated queries. We present a model for safe learning in safety-critical environments from human input that minimises bother cost. Our model, JPAL-HA, proposes an efficient mechanism to harness human preferences and justifications to significantly improve safety during the learning process without increasing the number of interactions with a user. We show this with both simulation and human experiments. 1

AAMAS Conference 2021 Conference Paper

Optimising Long-Term Outcomes using Real-World Fluent Objectives: An Application to Football

• Ryan Beal
• Georgios Chalkiadakis
• Timothy J. Norman
• Sarvapali D. Ramchurn

In this paper, we present a novel approach for optimising longterm tactical and strategic decision-making in football (soccer) by encapsulating events in a league environment across a given time frame. We model the teams’ objectives for a season and track how these evolve as games unfold to give a fluent objective that can aid in decision-making games. We develop Markov chain Monte Carlo and deep learning-based algorithms that make use of the fluent objectives in order to learn from prior games and other games in the environment and increase the teams’ long-term performance. Simulations of our approach using real-world datasets from 760 matches shows that by using optimised tactics with our fluent objective and prior games, we can on average increase teams mean expected finishing distribution in the league by up to 35. 6%.

AAMAS Conference 2021 Conference Paper

Responsibility Research for Trustworthy Autonomous Systems

• Vahid Yazdanpanah
• Enrico H. Gerding
• Sebastian Stein
• Mehdi Dastani
• Catholijn M. Jonker
• Timothy J. Norman

To develop and effectively deploy Trustworthy Autonomous Systems (TAS), we face various social, technological, legal, and ethical challenges in which different notions of responsibility can play a key role. In this work, we elaborate on these challenges, discuss research gaps, and show how the multidimensional notion of responsibility can play a role to bridge them. We argue that TAS requires operational tools to represent and reason about responsibilities of humans as well as AI agents. We review major challenges to which responsibility reasoning can contribute, highlight open research problems, and argue for the application of multiagent responsibility models in a variety of TAS domains.

KER Journal 2019 Journal Article

Artificial intelligence for team sports: a survey

• Ryan Beal
• Timothy J. Norman
• Sarvapali D. Ramchurn

Abstract The sports domain presents a number of significant computational challenges for artificial intelligence (AI) and machine learning (ML). In this paper, we explore the techniques that have been applied to the challenges within team sports thus far. We focus on a number of different areas, namely match outcome prediction, tactical decision making, player investments, fantasy sports, and injury prediction. By assessing the work in these areas, we explore how AI is used to predict match outcomes and to help sports teams improve their strategic and tactical decision making. In particular, we describe the main directions in which research efforts have been focused to date. This highlights not only a number of strengths but also weaknesses of the models and techniques that have been employed. Finally, we discuss the research questions that exist in order to further the use of AI and ML in team sports.

IJCAI Conference 2019 Conference Paper

Identifying vulnerabilities in trust and reputation systems

• Taha D. Güneş
• Long Tran-Thanh
• Timothy J. Norman

Online communities use trust and reputation systems to assist their users in evaluating other parties. Due to the preponderance of these systems, malicious entities have a strong incentive to attempt to influence them, and strategies employed are increasingly sophisticated. Current practice is to evaluate trust and reputation systems against known attacks, and hence are heavily reliant on expert analysts. We present a novel method for automatically identifying vulnerabilities in such systems by formulating the problem as a derivative-free optimisation problem and applying efficient sampling methods. We illustrate the application of this method for attacks that involve the injection of false evidence, and identify vulnerabilities in existing trust models. In this way, we provide reliable and objective means to assess how robust trust and reputation systems are to different kinds of attacks.

JAAMAS Journal 2017 Journal Article

Severity-sensitive norm-governed multi-agent planning

• Luca Gasparini
• Timothy J. Norman
• Martin J. Kollingbaum

Abstract In making practical decisions, agents are expected to comply with ideals of behaviour, or norms. In reality, it may not be possible for an individual, or a team of agents, to be fully compliant—actual behaviour often differs from the ideal. The question we address in this paper is how we can design agents that act in such a way that they select collective strategies to avoid more critical failures (norm violations), and mitigate the effects of violations that do occur. We model the normative requirements of a system through contrary-to-duty obligations and violation severity levels, and propose a novel multi-agent planning mechanism based on Decentralised POMDPs that uses a qualitative reward function to capture levels of compliance: N-Dec-POMDPs. We develop mechanisms for solving this type of multi-agent planning problem and show, through empirical analysis, that joint policies generated are equally as good as those produced through existing methods but with significant reductions in execution time.

AAMAS Conference 2016 Conference Paper

Decision Theoretic Norm-Governed Planning (Extended Abstract)

• Luca Gasparini
• Timothy J. Norman
• Martin J. Kollingbaum
• Liang Chen

We propose Normative Dec-POMDPs, a model of collective decision making in the presence of complex norms, with violations of norms classified according to their relative severity. We extend the PBPG algorithm in order to solve Normative Dec-POMDPs and propose a heuristic that improves its scalability without affecting the policy quality.

JAAMAS Journal 2016 Journal Article

How to trust a few among many

• Anthony Etuk
• Timothy J. Norman
• Mudhakar Srivatsa

Abstract The presence of numerous and disparate information sources available to support decision-making calls for efficient methods of harnessing their potential. Information sources may be unreliable, and misleading reports can affect decisions. Existing trust and reputation mechanisms typically rely on reports from as many sources as possible to mitigate the influence of misleading reports on decisions. In the real world, however, it is often the case that querying information sources can be costly in terms of energy, bandwidth, delay overheads, and other constraints. We present a model of source selection and fusion in resource-constrained environments, where there is uncertainty regarding the trustworthiness of sources. We exploit diversity among sources to stratify them into homogeneous subgroups to both minimise redundant sampling and mitigate the effect of certain biases. Through controlled experiments, we demonstrate that a diversity-based approach is robust to biases introduced due to dependencies among source reports, performs significantly better than existing approaches when sampling budget is limited and equally as good with an unlimited budget.

ECAI Conference 2016 Conference Paper

Observation-Based Multi-Agent Planning with Communication

• Luca Gasparini 0002
• Timothy J. Norman
• Martin J. Kollingbaum

Models of decentralized online planning vary in the information that individual agents use to make local action decisions. Some models consider only local observations, eschewing coordination through communication. Others use communication to ensure that all agents are aware of the action decisions of others, but assume costless and delay-free communication. In this paper, we propose a model of online planning (OB-MAP) that uses estimates of the value of communicating to manage coordination through communication as costs vary. We compare this approach to existing models in widely employed benchmark problems, demonstrating that OB-MAP performs significantly better in many scenarios regardless of varying (including infinite) cost of communication.

IS Journal 2014 Journal Article

Supporting Trust Assessment and Decision Making in Coalitions

• Chris Burnett
• Timothy J. Norman
• Katia Sycara
• Nir Oren

Modern multiorganizational coalitions can bring diverse sets of capabilities, assets, and information sources to bear on complex and dynamic operations. However, successfully completing these operations places demands on the trust between coalition partners. When it's necessary to rely on other partners, decision makers must be able to make rapid and effective trust assessments and decisions. Here, the authors focus on coalition information acquisition and discuss mechanisms for assessing trust and arriving at decisions about how to act when trust can be supplemented by controls. They also discuss future directions for these systems and highlight outstanding challenges.

EAAI Journal 2013 Journal Article

A hybrid reasoning mechanism for effective sensor selection for tasks

• Geeth De Mel
• Murat Sensoy
• Wamberto Vasconcelos
• Timothy J. Norman

In this paper, we present Ontological Logic Programming (OLP), a novel approach that combines logic programming with ontological reasoning. OLP enables the use of ontological terms (i. e. , individuals, classes and properties) directly within logic programmes. The interpretation of these terms is delegated to an ontology reasoner during the interpretation of the programme. Unlike similar approaches, OLP makes use of the full capacity of both ontological reasoning and logic programming. We evaluate the computational properties of OLP in different settings and show that its performance can be significantly improved using caching mechanisms. We then introduce a comprehensive sensor-task selection solution based on OLP and discuss the benefits one can obtain by using OLP. The solution is based on a set of interlinking ontologies that capture the crucial domain knowledge of sensor networks. We then make use of OLP to create and manage complex concepts in the domain as well as to implement effective resource-task assignment algorithms, which compute appropriate resources for tasks such that they sufficiently cover the tasks needs. We compare the advantages of OLP with a knowledge-based set-covering mechanism for resource-task selection.

EAAI Journal 2013 Journal Article

Prognostic normative reasoning

• Jean Oh
• Felipe Meneguzzi
• Katia Sycara
• Timothy J. Norman

Human users planning for multiple objectives in complex environments are subjected to high levels of cognitive workload, which can severely impair the quality of the plans created. This paper describes a software agent that can proactively assist cognitively overloaded users by providing normative reasoning about prohibitions and obligations so that the user can focus on her primary objectives. In order to provide proactive assistance, we develop the notion of prognostic normative reasoning (PNR) that consists of the following steps: (1) recognizing the user's planned activities, (2) reasoning about norms to evaluate those predicted activities, and (3) providing necessary assistance so that the user's activities are consistent with norms. The idea of PNR integrates various AI techniques, namely, user intention recognition, normative reasoning over a user's intention, and planning, execution and replanning for assistive actions. In this paper, we describe an agent architecture for PNR and discuss practical applications.

TIST Journal 2013 Journal Article

Stereotypical trust and bias in dynamic multiagent systems

• Chris Burnett
• Timothy J. Norman
• Katia Sycara

Large-scale multiagent systems have the potential to be highly dynamic. Trust and reputation are crucial concepts in these environments, as it may be necessary for agents to rely on their peers to perform as expected, and learn to avoid untrustworthy partners. However, aspects of highly dynamic systems introduce issues which make the formation of trust relationships difficult. For example, they may be short-lived, precluding agents from gaining the necessary experiences to make an accurate trust evaluation. This article describes a new approach, inspired by theories of human organizational behavior, whereby agents generalize their experiences with previously encountered partners as stereotypes, based on the observable features of those partners and their behaviors. Subsequently, these stereotypes are applied when evaluating new and unknown partners. Furthermore, these stereotypical opinions can be communicated within the society, resulting in the notion of stereotypical reputation. We show how this approach can complement existing state-of-the-art trust models, and enhance the confidence in the evaluations that can be made about trustees when direct and reputational information is lacking or limited. Furthermore, we show how a stereotyping approach can help agents detect unwanted biases in the reputational opinions they receive from others in the society.

ECAI Conference 2012 Conference Paper

An Empirical Study of Argumentation Schemes for Deliberative Dialogue

• Alice Toniolo
• Timothy J. Norman
• Katia P. Sycara

Collaborative decision making among agents in a team is a complex activity, and tasks to achieve individual objectives may conflict in a team context. A number of argumentation-based models have been proposed to address the problem, the rationale being that the revelation of background information and constraints can aid in the discovery and resolution of conflicts. To date, however, no empirical studies have been conducted to substantiate these claims. I this paper, we discuss a model, grounded on argumentation schemes, that captures potential conflicts due to scheduling and causality constraints, and individual goals and norms. We evaluate this model in complex collaborative planning problems and show that such a model facilitates the sharing of relevant information pertaining to plan, goal and normative conflicts. Further, we show that this focussed information sharing leads to more effective conflict resolution, particularly in the most challenging problems.

JAAMAS Journal 2012 Journal Article

Learning strategies for task delegation in norm-governed environments

• Chukwuemeka David Emele
• Timothy J. Norman
• Simon Parsons

Abstract How do I choose whom to delegate a task to? This is an important question for an autonomous agent collaborating with others to solve a problem. Were similar proposals accepted from similar agents in similar circumstances? What arguments were most convincing? What are the costs incurred in putting certain arguments forward? Can I exploit domain knowledge to improve the outcome of delegation decisions? In this paper, we present an agent decision-making mechanism where models of other agents are refined through evidence from past dialogues and domain knowledge, and where these models are used to guide future delegation decisions. Our approach combines ontological reasoning, argumentation and machine learning in a novel way, which exploits decision theory for guiding argumentation strategies. Using our approach, intelligent agents can autonomously reason about the restrictions (e. g. , policies/norms) that others are operating with, and make informed decisions about whom to delegate a task to. In a set of experiments, we demonstrate the utility of this novel combination of techniques. Our empirical evaluation shows that decision-theory, machine learning and ontology reasoning techniques can significantly improve dialogical outcomes.

IJCAI Conference 2011 Conference Paper

Agent-Oriented Incremental Team and Activity Recognition

• Daniele Masato
• Timothy J. Norman
• Wamberto W. Vasconcelos
• Katia Sycara

Monitoring team activity is beneficial when human teams cooperate in the enactment of a joint plan. Monitoring allows teams to maintain awareness of each other's progress within the plan and it enables anticipation of information needs. Humans find this difficult, particularly in time-stressed and uncertain environments. In this paper we introduce a probabilistic model, based on Conditional Random Fields, to automatically recognise the composition of teams and the team activities in relation to a plan. The team composition and activities are recognised incrementally by interpreting a stream of spatio-temporal observations.

IJCAI Conference 2011 Conference Paper

An Agent Architecture for Prognostic Reasoning Assistance

• Jean Oh
• Felipe Meneguzzi
• Katia Sycara
• Timothy J. Norman

In this paper we describe a software assistant agent that can proactively assist human users situated in a time-constrained environment to perform normative reasoning--reasoning about prohibitions and obligations--so that the user can focus on her planning objectives. In order to provide proactive assistance, the agent must be able to 1) recognize the user's planned activities, 2) reason about potential needs of assistance associated with those predicted activities, and 3) plan to provide appropriate assistance suitable for newly identified user needs. To address these specific requirements, we develop an agent architecture that integrates user intention recognition, normative reasoning over a user's intention, and planning, execution and replanning for assistive actions. This paper presents the agent architecture and discusses practical applications of this approach.

AAMAS Conference 2011 Conference Paper

Argumentation Strategies for Plan Resourcing

• Chukwuemeka D. Emele
• Timothy J. Norman
• Simon Parsons

What do I need to say to convince you to do something? This is an important question for an autonomous agent deciding whom to approach for a resource or for an action to be done. Were similar requests granted from similar agents in similar circumstances? What arguments were most persuasive? What are the costs involved in putting certain arguments forward? In this paper we present an agent decision-making mechanism where models of other agents are refined through evidence from past dialogues, and where these models are used to guide future argumentation strategy. We empirically evaluate our approach to demonstrate that decision-theoretic and machine learning techniques can both significantly improve the cumulative utility of dialogical outcomes, and help to reduce communication overhead.

EUMAS Conference 2011 Conference Paper

Argumentation Strategies for Task Delegation

• Chukwuemeka David Emele
• Timothy J. Norman
• Simon Parsons

Abstract What argument(s) do I put forward in order to persuade another agent to do something for me? This is an important question for an autonomous agent collaborating with others to solve a problem. How effective were similar arguments in convincing similar agents in similar circumstances? What are the risks associated with putting certain arguments forward? Can agents exploit evidence derived from past dialogues to improve the outcome of delegation decisions? In this paper, we present an agent decision-making mechanism where models of other agents are refined through evidence derived from dialogues, and where these models are used to guide future argumentation strategy. We combine argumentation, machine learning and decision theory in a novel way that enables agents to reason about constraints (e. g. , policies) that others are operating within, and make informed decisions about whom to delegate a task to. We demonstrate the utility of this novel approach through empirical evaluation in a plan resourcing domain. Our evaluation shows that a combination of decision-theoretic and machine learning techniques can significantly help to improve dialogical outcomes.

AAMAS Conference 2011 Conference Paper

Prognostic Normative Reasoning in Coalition Planning

• Jean Oh
• Felipe Meneguzzi
• Katia Sycara
• Timothy J. Norman

In this paper we describe a software assistant agent that can proactively assist human users situated in a time-constrained coalition environment. The cognitive workload is significantly increased when the user must not only cope with a complex environment, but also with a set of unaccustomed rules that prescribe how the coalition planning process must be carried out. In this context, we introduce the notion of prognostic norm reasoning to predict the user's likely normative violations, allowing the assistant agent to plan and take remedial actions before the violations actually occur. To the best of our knowledge, our approach is the first that manages norms in a proactive and autonomous manner.

IJCAI Conference 2011 Conference Paper

Trust Decision-Making in Multi-Agent Systems

• Chris Burnett
• Timothy J. Norman
• Katia Sycara

Trust is crucial in dynamic multi-agent systems, where agents may frequently join and leave, and the structure of the society may often change. In these environments, it may be difficult for agents to form stable trust relationships necessary for confident interactions. Societies may break down when trust between agents is too low to motivate interactions. In such settings, agents should make decisions about who to interact with, given their degree of trust in the available partners. We propose a decision-theoretic model of trust decision making allows controls to be used, as well as trust, to increase confidence in initial interactions. We consider explicit incentives, monitoring and reputation as examples of such controls. We evaluate our approach within a simulated, highly-dynamic multi-agent environment, and show how this model supports the making of delegation decisions when trust is low.

AIJ Journal 2010 Journal Article

A logic of delegation

• Timothy J. Norman
• Chris Reed

Delegation is a foundational concept for understanding and engineering systems that interact and execute tasks autonomously. By extending recent work on tensed action logic, it becomes possible to pin down a specific interpretation of responsibility with a well specified semantics and a convenient and intuitive logic for expression. Once descriptions of direct agent responsibility can be formed, there is a foundation upon which to characterise the dynamics of how responsibility can be acquired, transferred and discharged and, in particular, how delegation can be effected. The resulting logic, designed specifically to cater for responsibility and delegation, can then be employed to offer an axiological and semantic exploration of the related concepts of forbearance, imperatives and group communication.

AAMAS Conference 2009 Conference Paper

A Model for Integrating Dialogue and the Execution of Joint Plans

• Yuqing Tang
• Timothy J. Norman
• Simon Parsons

Coming up with a plan for a team that operates in a non-deterministic environment is a complex process, and the problem is further complicated by the need for team members to communicate while the plan is being executed. Such communication is required, for example, to make sure that information critical to the plan is passed in time for it to be useful. In this paper we present a model for constructing joint plans for a team of agents that takes into account their communication needs. The model builds on recent developments in symbolic non-deterministic planning, ideas that have not previously been applied to this problem.

JAAMAS Journal 2008 Journal Article

Normative conflict resolution in multi-agent systems

• Wamberto W. Vasconcelos
• Martin J. Kollingbaum
• Timothy J. Norman

Abstract Norms (permissions, obligations and prohibitions) offer a useful and powerful abstraction with which to capture social constraints in multi-agent systems. Norms should exclude disruptive or antisocial behaviour without prescribing the design of individual agents or restricting their autonomy. An important challenge, however, in the design and management of systems governed by norms is that norms may, at times, conflict with one another; e. g, an action may be simultaneously prohibited and obliged for a particular agent. In such circumstances, agents no longer have the option of complying with these norms; whatever they do or refrain from doing will lead to a social constraint being broken. In this paper, we present mechanisms for the detection and resolution of normative conflicts. These mechanisms, based on first-order unification and constraint solving techniques, are the building blocks of more sophisticated algorithms we present for the management of normative positions, that is, the adoption and removal of permissions, obligations and prohibitions in societies of agents. We capture both direct and indirect conflicts between norms, formalise a practical concept of authority, and model conflicts that may arise as a result of delegation. We are able to formally define classic ways for resolving conflicts such as lex superior and lex posterior.

JAAMAS Journal 2008 Journal Article

Organisational change through influence

• Mairi McCallum
• Wamberto W. Vasconcelos
• Timothy J. Norman

Abstract Influence is a phenomenon underpinning many types of interactions in both human and artificial organisations, and has a significant impact on the operation of the organisation. If influence can be examined at the organisational level, instead of at the level of the agents involved, engineers can better understand an organisation’s robustness to structural, behavioural and population changes. In this paper we present the Model of Organisational Change using Agents (MOChA) as a means to formally specify, check and simulate organisations using agents, particularly with a view to determining the impact of influence on the operation of an organisation. This formalisation of influence is not specific to our model, and is relevant and adaptable to any organisational model in which explicit relationships among roles of agents are formed.

AAMAS Conference 2007 Conference Paper

Resolving Conflict and Inconsistency in Norm-Regulated Virtual Organizations

• Wamberto Vasconcelos
• Martin J. Kollingbaum
• Timothy J. Norman

Norm-governed virtual organizations define, govern and facilitate coordinated resource sharing and problem solving in societies of agents. With an explicit account of norms, openness in virtual organizations can be achieved: new components, designed by various parties, can be seamlessly accommodated. We focus on virtual organizations realised as multi-agent systems, in which human and software agents interact to achieve individual and global goals. However, any realistic account of norms should address their dynamic nature: norms will change as agents interact with each other and their environment. Due to the changing nature of norms or due to norms stemming from different virtual organizations, there will be situations when an action is simultaneously permitted and prohibited, that is, a conflict arises. Likewise, there will be situations when an action is both obliged and prohibited, that is, an inconsistency arises. We introduce an approach, based on first-order unification, to detect and resolve such conflicts and inconsistencies. In our proposed solution, we annotate a norm with the set of values their variables should not have in order to avoid a conflict or an inconsistency with another norm. Our approach neatly accommodates the domain-dependent interrelations among actions and the indirect conflicts/inconsistencies these may cause. More generally, we can capture a useful notion of inter-agent (and inter-role) delegation of actions and norms associated to them, and use it to address conflicts/inconsistencies caused by action delegation. We illustrate our approach with an e-Science example in which agents support Grid services.

AIJ Journal 2007 Journal Article

Subjective logic and arguing with evidence

• Nir Oren
• Timothy J. Norman
• Alun Preece

This paper introduces a subjective logic based argumentation framework primarily targeted at evidential reasoning. The framework explicitly caters for argument schemes, accrual of arguments, and burden of proof; these concepts appear in many types of argument, and are particularly useful in dialogues revolving around evidential reasoning. The concept of a sensor is also useful in this domain, representing a source of evidence, and is incorporated in our framework. We show how the framework copes with a number of problems that existing frameworks have difficulty dealing with, and how it can be situated within a simple dialogue game. Finally, we examine reasoning machinery that enables an agent to decide what argument to advance with the goal of maximising its utility at the end of a dialogue.

ECAI Conference 2006 Conference Paper

Arguing with Confidential Information

• Nir Oren
• Timothy J. Norman
• Alun David Preece

While researchers have looked at many aspects of argumentation, an area often neglected is that of argumentation strategies. That is, given multiple possible arguments that an agent can put forth, which should be selected in what circumstances. In this paper, we propose a heuristic that implements one such strategy. The heuristic assigns a utility cost to revealing information, as well as a utility to winning, drawing and losing an argument. An agent participating in a dialogue then attempts to maximise its utility. We present a formal argumentation framework in which this heuristic may operate, and show how it functions within the framework. Finally, we discuss how this heuristic may be extended in future work, and its relevance to argumentation theory in general.

AAMAS Conference 2006 Conference Paper

CONOISE-G: Agent-based Virtual Organisations

• W. T. Luke Teacy
• Nicholas R. Jennings
• Michael Luck
• Stuart Chalmers
• Nir Oren
• Timothy J. Norman
• Alun Preece
• Peter M. D. Gray

AAMAS Conference 2003 Conference Paper

The NoA Agent Architecture - Implementing Normative Agents for Supervised Interaction

• Martin J. Kollingbaum
• Timothy J. Norman

AAMAS Conference 2002 Conference Paper

Supervised Interaction - Creating a Web of Trust for Contracting Agents in Electronic Environments

• Martin J. Kollingbaum
• Timothy J. Norman