18 citations · 37 across the 14 of their papers we have counts for
16 papers
The Benefits of Interaction Constraints in Distributed Autonomous Systems
Michael Crosscombe, Jonathan Lawry
The design of distributed autonomous systems often omits consideration of the underlying network dynamics. Recent works in multi-agent systems and swarm robotics alike have highlig…
Learning Interpretable Models of Aircraft Handling Behaviour by Reinforcement Learning from Human Feedback
Tom Bewley, Jonathan Lawry, Arthur Richards
We propose a method to capture the handling abilities of fast jet pilots in a software model via reinforcement learning (RL) from human preference feedback. We use pairwise prefere…
Two-step counterfactual generation for OOD examples
Nawid Keshtmand, Raul Santos-Rodriguez, Jonathan Lawry
Two fundamental requirements for the deployment of machine learning models in safety-critical systems are to be able to detect out-of-distribution (OOD) data correctly and to be ab…
Understanding the properties and limitations of contrastive learning for Out-of-Distribution detection
Nawid Keshtmand, Raul Santos-Rodriguez, Jonathan Lawry
A recent popular approach to out-of-distribution (OOD) detection is based on a self-supervised learning technique referred to as contrastive learning. There are two main variants o…
Reward Learning with Trees: Methods and Evaluation
Tom Bewley, Jonathan Lawry, Arthur Richards +2
Recent efforts to learn reward functions from human feedback have tended to use deep neural networks, whose lack of transparency hampers our ability to explain agent behaviour or v…
Summarising and Comparing Agent Dynamics with Contrastive Spatiotemporal Abstraction
Tom Bewley, Jonathan Lawry, Arthur Richards
We introduce a data-driven, model-agnostic technique for generating a human-interpretable summary of the salient points of contrast within an evolving dynamical system, such as the…
The Impact of Network Connectivity on Collective Learning
Michael Crosscombe, Jonathan Lawry
In decentralised autonomous systems it is the interactions between individual agents which govern the collective behaviours of the system. These local-level interactions are themse…
TripleTree: A Versatile Interpretable Representation of Black Box Agents and their Environments
Tom Bewley, Jonathan Lawry
In explainable artificial intelligence, there is increasing interest in understanding the behaviour of autonomous agents to build trust and validate performance. Modern agent archi…
Modelling Agent Policies with Interpretable Imitation Learning
Tom Bewley, Jonathan Lawry, Arthur Richards
As we deploy autonomous agents in safety-critical domains, it becomes important to develop an understanding of their internal mechanisms and representations. We outline an approach…
Distributed Possibilistic Learning in Multi-Agent Systems
Jonathan Lawry, Michael Crosscombe, David Harvey
Possibility theory is proposed as an uncertainty representation framework for distributed learning in multi-agent systems and robot swarms. In particular, we investigate its applic…
A Model of Multi-Agent Consensus for Vague and Uncertain Beliefs
Michael Crosscombe, Jonathan Lawry
Consensus formation is investigated for multi-agent systems in which agents' beliefs are both vague and uncertain. Vagueness is represented by a third truth state meaning \emph{bor…
A Fuzzy Approach to Qualification in Design Exploration for Autonomous Robots and Systems
Jeremy Morse, Dejanira Araiza-Illan, Jonathan Lawry +2
Autonomous robots must operate in complex and changing environments subject to requirements on their behaviour. Verifying absolute satisfaction (true or false) of these requirement…
Formal Specification and Analysis of Autonomous Systems under Partial Compliance
Jeremy Morse, Dejanira Araiza-Illan, Jonathan Lawry +2
The widespread adoption of autonomous systems depends on providing guarantees of safety and functional correctness, at both design time and runtime. Information about the extent to…
Emerging Dimension Weights in a Conceptual Spaces Model of Concept Combination
Martha Lewis, Jonathan Lawry
We investigate the generation of new concepts from combinations of properties as an artificial language develops. To do so, we have developed a new framework for conjunctive concep…
The Utility of Hedged Assertions in the Emergence of Shared Categorical Labels
Martha Lewis, Jonathan Lawry
We investigate the emergence of shared concepts in a community of language users using a multi-agent simulation. We extend results showing that negated assertions are of use in dev…
A Label Semantics Approach to Linguistic Hedges
Martha Lewis, Jonathan Lawry
We introduce a model for the linguistic hedges `very' and `quite' within the label semantics framework, and combined with the prototype and conceptual spaces theories of concepts.…