We work on algorithms for agents to adapt to new teammates in ad hoc multi-agent teams. We focus on zero-shot coordination (ZSC), where agents have to adapt to new, unseen teammates with no additional learning.

This capability could be useful, for example, in a search-and-rescue mission where robots are deployed from different organizations and expected to cooperate with each other on the fly. These robots may have different biases in how they achieve a given objective (e.g., risky vs. risk-averse search) or have different capabilities (e.g., sensing vs. manipulation).

---

---

This work was funded in part by ONR N00014-20-1-2249.