Abstract

In a wide range of scenarios, individual decision-makers consume information revealed by the previous decisions, and produce information that may help in the future decisions. Each decision-maker would individually prefer to "exploit" (optimize the current reward), but would like the previous agents to "explore" (try out various alternatives). A social planner, by means of carefully designed information disclosure, can incentivize the agents to balance exploration and exploitation so as to maximize social welfare. We overview the current state of this problem space, and highlight some recent developments.

Attachment

Video Recording