Assisting Unknown Teammates in Unknown Tasks: Ad Hoc Teamwork under Partial Observability
This addresses the challenge of flexible, on-the-fly collaboration in multi-agent systems for applications like robotics or gaming, though it is incremental by extending prior work to partial observability.
The paper tackled the problem of ad hoc teamwork under partial observability, enabling collaboration with unknown teammates on unknown tasks without pre-coordination, and showed that their Bayesian algorithm effectively identifies tasks from a large library and solves them in near-optimal time.
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.