Ad Hoc Teamwork in Variations of the Pursuit Domain

AAAI 2011 pp. 1758-1759

doi:10.1609/AAAI.V25I1.8054 /aaai/2011/barrett2011aaai-ad/

Abstract

In multiagent team settings, the agents are often given a protocol for coordinating their actions. When such a protocol is not available, agents must engage in ad hoc teamwork to effectively cooperate with one another. A fully general ad hoc team agent needs to be capable of collaborating with a wide range of potential teammates on a varying set of joint tasks. This paper extends previous research in a new direction with the introduction of an efficient method for reasoning about the value of information. Then, we show how previous theoretical results can aid ad hoc agents in a set of testbed pursuit domains.

PDF AAAI Semantic Scholar

Cite

Text

Barrett and Stone. "Ad Hoc Teamwork in Variations of the Pursuit Domain." AAAI Conference on Artificial Intelligence, 2011. doi:10.1609/AAAI.V25I1.8054

Markdown

[Barrett and Stone. "Ad Hoc Teamwork in Variations of the Pursuit Domain." AAAI Conference on Artificial Intelligence, 2011.](https://mlanthology.org/aaai/2011/barrett2011aaai-ad/) doi:10.1609/AAAI.V25I1.8054

BibTeX

@inproceedings{barrett2011aaai-ad,
  title     = {{Ad Hoc Teamwork in Variations of the Pursuit Domain}},
  author    = {Barrett, Samuel and Stone, Peter},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2011},
  pages     = {1758-1759},
  doi       = {10.1609/AAAI.V25I1.8054},
  url       = {https://mlanthology.org/aaai/2011/barrett2011aaai-ad/}
}