Robby is Not a Robber (anymore): On the Use of Institutions for Learning Normative Behavior
This addresses the challenge of making robots socially acceptable and useful in human society, though it appears incremental in applying existing norm concepts to reinforcement learning.
The paper tackles the problem of enabling robots to follow human social norms by using a framework that captures social knowledge as norms to guide reinforcement learning agents, achieving normative behavior across different domains with a method independent of specific RL algorithms.
Future robots should follow human social norms in order to be useful and accepted in human society. In this paper, we leverage already existing social knowledge in human societies by capturing it in our framework through the notion of social norms. We show how norms can be used to guide a reinforcement learning agent towards achieving normative behavior and apply the same set of norms over different domains. Thus, we are able to: (1) provide a way to intuitively encode social knowledge (through norms); (2) guide learning towards normative behaviors (through an automatic norm reward system); and (3) achieve a transfer of learning by abstracting policies; Finally, (4) the method is not dependent on a particular RL algorithm. We show how our approach can be seen as a means to achieve abstract representation and learn procedural knowledge based on the declarative semantics of norms and discuss possible implications of this in some areas of cognitive science.