Feature-based Joint Planning and Norm Learning in Collaborative Games.
Mark K. Ho, James MacGlashan, Amy Greenwald, Michael L. Littman, Elizabeth Hilliard, Carl Trimbach, Stephen Brawner, Josh Tenenbaum, Max Kleiman‐Weiner, Joseph L. Austerweil · eScholarship (California Digital Library) · 2016
People often use norms to coordinate behavior andaccomplish shared goals. But how do people learn andrepresent norms? Here, we formalize the process by whichcollaborating individuals (1) reason about group plans duringinteraction, and (2) use task features to abstractly representnorms. In Experiment 1, we test the assumptions of our modelin a gridworld that requires coordination and contrast it with a“best response” model. In Experiment 2, we use our model totest whether group members’ joint planning relies more onstate features independent of other agents (landmark-basedfeatures) or state features determined by the configuration ofagents (agent-relative features).