Foundations of Cooperative AI

Abstract

AI systems can interact in unexpected ways, sometimes with disastrous consequences. As AI gets to control more of our world, these interactions will become more common and have higher stakes. As AI becomes more advanced, these interactions will become more sophisticated, and game theory will provide the tools for analyzing these interactions. However, AI agents are in some ways unlike the agents traditionally studied in game theory, introducing new challenges as well as opportunities. We propose a research agenda to develop the game theory of highly advanced AI agents, with a focus on achieving cooperation.

Cite

Text

Conitzer and Oesterheld. "Foundations of Cooperative AI." AAAI Conference on Artificial Intelligence, 2023. doi:10.1609/AAAI.V37I13.26791

Markdown

[Conitzer and Oesterheld. "Foundations of Cooperative AI." AAAI Conference on Artificial Intelligence, 2023.](https://mlanthology.org/aaai/2023/conitzer2023aaai-foundations/) doi:10.1609/AAAI.V37I13.26791

BibTeX

@inproceedings{conitzer2023aaai-foundations,
  title     = {{Foundations of Cooperative AI}},
  author    = {Conitzer, Vincent and Oesterheld, Caspar},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2023},
  pages     = {15359-15367},
  doi       = {10.1609/AAAI.V37I13.26791},
  url       = {https://mlanthology.org/aaai/2023/conitzer2023aaai-foundations/}
}