Results for "game theory"
Agents optimize collective outcomes.
Agents have opposing objectives.
Combination of cooperation and competition.
Designing efficient marketplaces.
Feature attribution method grounded in cooperative game theory for explaining predictions in tabular settings.
No agent benefits from unilateral deviation.
Some agents know more than others.
Agents fail to coordinate optimally.
Designing systems where rational agents behave as desired.
Model exploits poorly specified objectives.
Two-network setup where generator fools a discriminator.
Research ensuring AI remains safe.
Multiple agents interacting cooperatively or competitively.
Tendency for agents to pursue resources regardless of final goal.
Willingness of system to accept correction or shutdown.
Ensuring AI allows shutdown.
Risk threatening humanity’s survival.
Competitive advantage from proprietary models/data.
Compromising AI systems via libraries, models, or datasets.
No agent can improve without hurting another.
Requirement to provide explanations.
Rules governing auctions.
Protection of private legal communications.
Competition arises without explicit design.
AI tacitly coordinating prices.
Market reacting strategically to AI.
Emergence of conventions among agents.
Tendency to gain control/resources.
Designing AI to cooperate with humans and each other.
Decisions dependent on others’ actions.