@COMMENT This file was generated by bib2html.pl <http://www.cs.cmu.edu/~pfr/misc_software/index.html#bib2html> version 0.90
@COMMENT written by Patrick Riley <http://www.cs.cmu.edu/~pfr>
@COMMENT This file came from Peter Stone's publication pages at
@COMMENT http://www.cs.utexas.edu/~pstone/papers
@InProceedings{wang-naht-24,
  author   = {Caroline Wang and Arrasy Rahman and Ishan Durugkar and Elad Liebman and Peter Stone},
  title    = {N-Agent Ad Hoc Teamwork},
  booktitle = {Conference on Neural Information Processing Systems (NeurIPS)},
  year     = {2024},
  month    = {December},
  location = {Vancouver, Canada},
  abstract = {Current approaches to learning cooperative multi-agent behaviors assume
relatively restrictive settings. In standard fully cooperative multi-agent
reinforcement learning, the learning algorithm controls all agents in the
scenario, while in ad hoc teamwork, the learning algorithm usually assumes
control over only a single agent in the scenario. However, many cooperative
settings in the real world are much less restrictive. For example, in an
autonomous driving scenario, a company might train its cars with the same
learning algorithm, yet once on the road, these cars must cooperate with cars
from another company. Towards expanding the class of scenarios that cooperative
learning methods may optimally address, we introduce N-agent ad hoc teamwork
(NAHT), where a set of autonomous agents must interact and cooperate with
dynamically varying numbers and types of teammates. This paper formalizes the
problem, and proposes the Policy Optimization with Agent Modelling (POAM)
algorithm. POAM is a policy gradient, multi-agent reinforcement learning approach
to the NAHT problem that enables adaptation to diverse teammate behaviors by
learning representations of teammate behaviors. Empirical evaluation on tasks
from the multi-agent particle environment and StarCraft II shows that POAM
improves cooperative task returns compared to baseline approaches, and enables
out-of-distribution generalization to unseen teammates.
  },
}