Statements (28)
Predicate | Object |
---|---|
gptkbp:instanceOf |
field of artificial intelligence
|
gptkbp:address |
trust in AI systems
coordination problems communication between agents fairness in multi-agent interactions |
gptkbp:aimsTo |
improve outcomes in environments with multiple agents
|
gptkbp:discusses |
gptkb:AAAI
gptkb:ICML gptkb:NeurIPS |
gptkbp:emergedIn |
2010s
|
gptkbp:focusesOn |
enabling AI systems to cooperate with humans and other AI systems
|
gptkbp:goal |
align AI systems with human values in cooperative settings
|
gptkbp:hasApplication |
autonomous vehicles
robotics resource allocation social dilemmas distributed AI negotiation systems |
https://www.w3.org/2000/01/rdf-schema#label |
Cooperative AI
|
gptkbp:relatedTo |
game theory
multi-agent systems mechanism design human-AI collaboration |
gptkbp:studiedBy |
gptkb:DeepMind
gptkb:Microsoft_Research academic institutions |
gptkbp:bfsParent |
gptkb:Richard_Ngo
|
gptkbp:bfsLayer |
8
|