Dynamics of Moral Behavior in Heterogeneous Populations of Learning Agents

arXiv:2403.04202v1 Announce Type: cross
Abstract: Growing concerns about safety and alignment of AI systems highlight the importance of embedding moral capabilities in artificial agents. A promising solution is the use of learning from experience, i.e., Reinforcement Learning. In multi-agent (social) environments, complex population-level phenomena may emerge from interactions between individual learning agents. Many of the existing studies rely on simulated social dilemma environments to study the interactions of independent learning agents. However, they tend to ignore the moral heterogeneity that …

abstract agent agents ai systems alignment artificial arxiv behavior capabilities concerns cs.ai cs.cy cs.lg cs.ma dynamics embedding environments experience highlight importance interactions multi-agent population reinforcement reinforcement learning safety social solution systems type