Search Results for author:
Found 15 papers, 1 papers with code
Learning Interpretable Models of Aircraft Handling Behaviour by Reinforcement Learning from Human Feedback
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.
Two-step counterfactual generation for OOD examples
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.
Understanding the properties and limitations of contrastive learning for Out-of-Distribution detection
We see that OOD samples tend to be classified into classes that have a distribution similar to the distribution of the entire dataset.
Reward Learning with Trees: Methods and Evaluation
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.
Summarising and Comparing Agent Dynamics with Contrastive Spatiotemporal Abstraction
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.
The Impact of Network Connectivity on Collective Learning
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.
TripleTree: A Versatile Interpretable Representation of Black Box Agents and their Environments
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
Modelling Agent Policies with Interpretable Imitation Learning
As we deploy autonomous agents in safety-critical domains, it becomes important to develop an understanding of their internal mechanisms and representations.
Evidence Propagation and Consensus Formation in Noisy Environments
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.
A Model of Multi-Agent Consensus for Vague and Uncertain Beliefs
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.
Exploiting Vagueness for Multi-Agent Consensus
A framework for consensus modelling is introduced using Kleene's three valued logic as a means to express vagueness in agents' beliefs.
The Utility of Hedged Assertions in the Emergence of Shared Categorical Labels
Results show that using hedged assertions positively affects the emergence of shared categories in two distinct ways.
Concept Generation in Language Evolution
This thesis investigates the generation of new concepts from combinations of existing concepts as a language evolves.
A Label Semantics Approach to Linguistic Hedges
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.
Emerging Dimension Weights in a Conceptual Spaces Model of Concept Combination
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.
