Showing cs.AIShow all
2 papers · 1 filter
cs.AI2025
Informative Communication of Robot Plans
Michele Persiani, Thomas Hellstrom
When a robot is asked to verbalize its plan it can do it in many ways. For example, a seemingly natural strategy is incremental, where the robot verbalizes its planned actions in p…
cs.AI2022
Policy Regularization for Legible Behavior
Michele Persiani, Thomas Hellström
In Reinforcement Learning interpretability generally means to provide insight into the agent's mechanisms such that its decisions are understandable by an expert upon inspection. T…