Incorporating Rich Social Interactions Into MDPs
Ravi Tejwani, Yen-Ling Kuo, Tianmin Shu, Bennett Stankovits, Dan, Gutfreund, Joshua B. Tenenbaum, Boris Katz, Andrei Barbu

TL;DR
This paper introduces a formal framework extending Markov Decision Processes to model complex social interactions like cooperation and conflict, enabling robots to engage socially in novel environments without prior examples.
Contribution
It formalizes social interactions within MDPs using microsociology and economics, allowing robots to perform and recognize social behaviors zero-shot.
Findings
Robots can execute social interactions in new environments without prior training.
Social MDPs align closely with human judgments of social interactions.
The framework provides concrete mathematical definitions for social behaviors.
Abstract
Much of what we do as humans is engage socially with other agents, a skill that robots must also eventually possess. We demonstrate that a rich theory of social interactions originating from microsociology and economics can be formalized by extending a nested MDP where agents reason about arbitrary functions of each other's hidden rewards. This extended Social MDP allows us to encode the five basic interactions that underlie microsociology: cooperation, conflict, coercion, competition, and exchange. The result is a robotic agent capable of executing social interactions zero-shot in new environments; like humans it can engage socially in novel ways even without a single example of that social interaction. Moreover, the judgments of these Social MDPs align closely with those of humans when considering which social interaction is taking place in an environment. This method both sheds light…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMulti-Agent Systems and Negotiation · Computability, Logic, AI Algorithms · Reinforcement Learning in Robotics
