253 citations · 296 across the 6 of their papers we have counts for
Showing 2021Show all
2 papers · 1 filter
cs.RO2021
Causal versus Marginal Shapley Values for Robotic Lever Manipulation Controlled using Deep Reinforcement Learning
Sindre Benjamin Remman, Inga Strümke, Anastasios M. Lekkas
We investigate the effect of including domain knowledge about a robotic system's causal relations when generating explanations. To this end, we compare two methods from explainable…
cs.LG2021★ 2 cited
Inferring feature importance with uncertainties in high-dimensional data
Pål Vegard Johnsen, Inga Strümke, Signe Riemer-Sørensen +2
Estimating feature importance is a significant aspect of explaining data-based models. Besides explaining the model itself, an equally relevant question is which features are impor…