no code implementations • 26 May 2023 • 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.
no code implementations • 10 Feb 2023 • 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 able to explain the prediction of the model.
no code implementations • 6 Nov 2022 • Nawid Keshtmand, Raul Santos-Rodriguez, Jonathan Lawry
We see that OOD samples tend to be classified into classes that have a distribution similar to the distribution of the entire dataset.
no code implementations • 3 Oct 2022 • Tom Bewley, Jonathan Lawry, Arthur Richards, Rachel Craddock, Ian Henderson
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 verify alignment.
no code implementations • 17 Jan 2022 • 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 learning process of a control agent.
no code implementations • 1 Jun 2021 • Michael Crosscombe, Jonathan Lawry
Models for collective behaviours may often rely upon the assumption of total connectivity between agents to provide effective information sharing within the system, but this assumption may be ill-advised.
1 code implementation • 10 Sep 2020 • 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.
Explainable artificial intelligence reinforcement-learning +1
no code implementations • 19 Jun 2020 • 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.
no code implementations • 13 May 2019 • Michael Crosscombe, Jonathan Lawry, Palina Bartashevich
Results show that a combination of updating on direct evidence and belief combination between agents results in better consensus to the best state than does evidence updating alone.
no code implementations • 11 Dec 2016 • Michael Crosscombe, Jonathan Lawry
Finally, if agent interactions are guided by belief quality measured as similarity to the true state of the world, then applying the consensus operator alone results in the population converging to a high quality shared belief.
no code implementations • 19 Jul 2016 • Michael Crosscombe, Jonathan Lawry
A framework for consensus modelling is introduced using Kleene's three valued logic as a means to express vagueness in agents' beliefs.
no code implementations • 25 Jan 2016 • Martha Lewis, Jonathan Lawry
Results show that using hedged assertions positively affects the emergence of shared categories in two distinct ways.
no code implementations • 25 Jan 2016 • Martha Lewis, Jonathan Lawry
This thesis investigates the generation of new concepts from combinations of existing concepts as a language evolves.
no code implementations • 25 Jan 2016 • 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.
no code implementations • 25 Jan 2016 • Martha Lewis, Jonathan Lawry
The expected value and the variance of these weights across agents may be predicted from the distribution of elements in the conceptual space, as determined by the underlying environment, together with the rate at which agents adopt others' concepts.