Balancing utility and cognitive cost in social representation
This addresses the challenge for AI agents in managing cognitive resources when representing other agents, but it appears incremental as it builds on existing concepts without claiming major breakthroughs.
The paper tackles the problem of constructing agent representations that balance downstream utility and information cost, using selective social learning as an example task, and illustrates two example approaches to resource-constrained social representation.
To successfully navigate its environment, an agent must construct and maintain representations of the other agents that it encounters. Such representations are useful for many tasks, but they are not without cost. As a result, agents must make decisions regarding how much information they choose to store about the agents in their environment. Using selective social learning as an example task, we motivate the problem of finding agent representations that optimally trade off between downstream utility and information cost, and illustrate two example approaches to resource-constrained social representation.