@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
@Techreport{mcalinden26,
  author   = {Andrew McAlinden and Caroline Wang and Steven Shi and Arrasy Rahman and Elad Liebman and Peter Stone},
  title    = {Centralized Critics for N-Agent Ad Hoc Teamwork},
  institution = "arXiv", 
  number = "arXiv e-Prints 2610.34799",
  year     = {2026},
  month = {October},  	   
  abstract = {
              Centralized training with decentralized execution (CTDE)
              has become the dominant paradigm in multi-agent
              reinforcement learning (MARL), motivating extensive
              study of what privileged information should be made
              available to the critic during training. While prior
              work has examined the role of global state in fully
              cooperative settings, the design of centralized critics
              for N-agent ad hoc teamwork - in which dynamically
              varying set of learning agents must coordinate with an
              arbitrary set of uncontrolled teammates drawn from an
              unknown distribution - remains poorly understood. We
              study this question by comparing two natural classes of
              advantage estimators: controlled history estimators,
              which condition only on the observation and action
              histories of the learner's own agents, and joint history
              estimators, which additionally condition on the
              histories of the uncontrolled teammates. We prove that
              both estimators are unbiased and characterize the
              conditions under which the joint history estimate
              attains strictly lower variance than its controlled
              counterpart. Empirically, joint history critics match or
              outperform controlled history critics across a range of
              NAHT tasks, yielding improved sample efficiency and
              final returns. Together, these results provide both a
              theoretical justification and an empirical
              recommendation for incorporating uncontrolled agent
              histories into centralized critics for N-agent ad hoc
              teamwork.},
  wwwnote={<a href="https://arxiv.org/abs/2610.34799">arXiv version</a>},
}