Assisting Unknown Teammates in Unknown Tasks: Ad Hoc Teamwork under Partial Observability

TL;DR

This paper introduces a Bayesian online prediction algorithm for ad hoc teamwork under partial observability, enabling real-time collaboration with unknown teammates performing unknown tasks without prior coordination.

Contribution

It presents a novel method that handles partial observability and unknown teammates/tasks, advancing ad hoc teamwork capabilities in complex environments.

Findings

Effective in identifying teammates' tasks from large libraries

Achieves near-optimal solution times

Scales well with larger problem sizes

Abstract

In this paper, we present a novel Bayesian online prediction algorithm for the problem setting of ad hoc teamwork under partial observability (ATPO), which enables on-the-fly collaboration with unknown teammates performing an unknown task without needing a pre-coordination protocol. Unlike previous works that assume a fully observable state of the environment, ATPO accommodates partial observability, using the agent's observations to identify which task is being performed by the teammates. Our approach assumes neither that the teammate's actions are visible nor an environment reward signal. We evaluate ATPO in three domains -- two modified versions of the Pursuit domain with partial observability and the overcooked domain. Our results show that ATPO is effective and robust in identifying the teammate's task from a large library of possible tasks, efficient at solving it in near-optimal time, and scalable in adapting to increasingly larger problem sizes.