4 papers
Do Machines Fail Like Humans? A Human-Centred Out-of-Distribution Spectrum for Mapping Error Alignment
Binxia Xu, Xiaoliang Luo, Luke Dickens +1
Determining whether AI systems process information similarly to humans is central to cognitive science and trustworthy AI. While modern AI models can match human accuracy on standa…
Predictive Representations for Skill Transfer in Reinforcement Learning
Ruben Vereecken, Luke Dickens, Alessandra Russo
A key challenge in scaling up Reinforcement Learning is generalizing learned behaviour. Without the ability to carry forward acquired knowledge an agent is doomed to learn each tas…
Disentangling Neural Disjunctive Normal Form Models
Kexin Gu Baugh, Vincent Perreault, Matthew Baugh +3
Neural Disjunctive Normal Form (DNF) based models are powerful and interpretable approaches to neuro-symbolic learning and have shown promising results in classification and reinfo…
Neural DNF-MT: A Neuro-symbolic Approach for Learning Interpretable and Editable Policies
Kexin Gu Baugh, Luke Dickens, Alessandra Russo
Although deep reinforcement learning has been shown to be effective, the model's black-box nature presents barriers to direct policy interpretation. To address this problem, we pro…