Cooperative AI

Applied to GovAI Annual Report 2021 by Leo at 8mo

Cooperative AI is a subfield of AIartificial intelligence that aims to improve the ability of AI systems to engender cooperation between humans, machines, and institutions. It can therefore also be seen as part of the AI safety landscape, aimed at preventing AI risks and x-existential risks resulting from cooperation failure.

Cooperative AI is a subfield of AI that aims to improve the ability of AI systems to engender cooperation between humans, machines, and institutions. It can therefore also be seen as part of the AI safety landscape, aimed at preventing AI risks and x-risks resulting from cooperation failure.

Further Reading

  • A. Dafoe, Y. Bachrach, G. Hadfield, E. Horvitz, K. Larson and T. Graepel, "Cooperative AI: Machines Must Learn to Find Common Ground," Nature593, 33-36 (2021).
  • A. Dafoe, E. Hughes, Y. Bachrach, T. Collins, K. R. McKee, J. Z. Leibo, K. Larson and T. Graepel, "Open Problems in Cooperative AI,"  arXiv:2012.08630 (2020).

Related Entries

Cooperative AI Foundation | AI safety

Created by Lewis Hammond at 8mo