154 citations · 471 across the 17 of their papers we have counts for
3 papers · 1 filter
Doing the right thing for the right reason: Evaluating artificial moral cognition by probing cost insensitivity
Yiran Mao, Madeline G. Reinecke, Markus Kunesch +4
Is it possible to evaluate the moral cognition of complex artificial agents? In this work, we take a look at one aspect of morality: `doing the right thing for the right reasons.'…
Heterogeneous Social Value Orientation Leads to Meaningful Diversity in Sequential Social Dilemmas
Udari Madhushani, Kevin R. McKee, John P. Agapiou +6
In social psychology, Social Value Orientation (SVO) describes an individual's propensity to allocate resources between themself and others. In reinforcement learning, SVO has been…
Diversity Through Exclusion (DTE): Niche Identification for Reinforcement Learning through Value-Decomposition
Peter Sunehag, Alexander Sasha Vezhnevets, Edgar Duéñez-Guzmán +2
Many environments contain numerous available niches of variable value, each associated with a different local optimum in the space of behaviors (policy space). In such situations i…