Results for "physical agents"
Modeling environment evolution in latent space.
Imagined future trajectories.
Acting to minimize surprise or free energy.
Perceived actions an environment allows.
Humans assist or override autonomous behavior.
Robots learning via exploration and growth.
Learning without catastrophic forgetting.
Combination of cooperation and competition.
No agent benefits from unilateral deviation.
Rules governing auctions.
Designing efficient marketplaces.
System-level behavior arising from interactions.
Early signals disproportionately influence outcomes.
Existential risk from AI systems.
Internal representation of the agent itself.
Tendency to gain control/resources.
Research ensuring AI remains safe.
Decisions dependent on others’ actions.
Risk threatening humanity’s survival.