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

01/10/2022
by   João G. Ribeiro, et al.
0

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.

READ FULL TEXT

page 5

page 8

research
10/11/2022

A General Learning Framework for Open Ad Hoc Teamwork Using Graph-based Policy Learning

Open ad hoc teamwork is the problem of training a single agent to effici...
research
05/06/2022

Learning to Cooperate with Completely Unknown Teammates

A key goal of ad hoc teamwork is to develop a learning agent that cooper...
research
06/01/2023

Knowledge-based Reasoning and Learning under Partial Observability in Ad Hoc Teamwork

Ad hoc teamwork refers to the problem of enabling an agent to collaborat...
research
06/03/2015

A Game-Theoretic Model and Best-Response Learning Method for Ad Hoc Coordination in Multiagent Systems

The ad hoc coordination problem is to design an autonomous agent which i...
research
06/19/2023

Controlling Type Confounding in Ad Hoc Teamwork with Instance-wise Teammate Feedback Rectification

Ad hoc teamwork requires an agent to cooperate with unknown teammates wi...
research
02/10/2019

Learning Best Response Strategies for Agents in Ad Exchanges

Ad exchanges are widely used in platforms for online display advertising...
research
04/12/2021

From partners to populations: A hierarchical Bayesian account of coordination and convention

Languages are powerful solutions to coordination problems: they provide ...

Please sign up or login with your details

Forgot password? Click here to reset