3 papers
cs.LG2025
Active Query Selection for Crowd-Based Reinforcement Learning
Jonathan Erskine, Taku Yamagata, Raúl Santos-Rodríguez
Preference-based reinforcement learning has gained prominence as a strategy for training agents in environments where the reward signal is difficult to specify or misaligned with h…
cs.LG2024
Learning Confidence Bounds for Classification with Imbalanced Data
Matt Clifford, Jonathan Erskine, Alexander Hepburn +2
Class imbalance poses a significant challenge in classification tasks, where traditional approaches often lead to biased models and unreliable predictions. Undersampling and oversa…
cs.LG2024
An Interactive Human-Machine Learning Interface for Collecting and Learning from Complex Annotations
Jonathan Erskine, Matt Clifford, Alexander Hepburn +1
Human-Computer Interaction has been shown to lead to improvements in machine learning systems by boosting model performance, accelerating learning and building user confidence. In…