225 citations · 521 across the 12 of their papers we have counts for
14 papers
Active Inference and Human--Computer Interaction
Roderick Murray-Smith, John H. Williamson, Sebastian Stein
Active Inference is a closed-loop computational theoretical basis for understanding behaviour, based on agents with internal probabilistic generative models that encode their belie…
Learning Robust Controllers Via Probabilistic Model-Based Policy Search
Valentin Charvet, Bjørn Sand Jensen, Roderick Murray-Smith
Model-based Reinforcement Learning estimates the true environment through a world model in order to approximate the optimal policy. This family of algorithms usually benefits from…
Forward and Inverse models in HCI:Physical simulation and deep learning for inferring 3D finger pose
Roderick Murray-Smith, John H. Williamson, Andrew Ramsay +3
We outline the role of forward and inverse modelling approaches in the design of human--computer interaction systems. Causal, forward models tend to be easier to specify and simula…
Max-Utility Based Arm Selection Strategy For Sequential Query Recommendations
Shameem A. Puthiya Parambath, Christos Anagnostopoulos, Roderick Murray-Smith +2
We consider the query recommendation problem in closed loop interactive learning settings like online information gathering and exploratory analytics. The problem can be naturally…
IntenT5: Search Result Diversification using Causal Language Models
Sean MacAvaney, Craig Macdonald, Roderick Murray-Smith +1
Search result diversification is a beneficial approach to overcome under-specified queries, such as those that are ambiguous or multi-faceted. Existing approaches often rely on mas…
Intermittent control as a model of mouse movements
J. Alberto Álvarez Martín, Henrik Gollee, Jörg Müller +1
We present Intermittent Control (IC) models as a candidate framework for modelling human input movements in Human--Computer Interaction (HCI). IC differs from continuous control in…