Incentivized Learning in Principal-Agent Bandit Games

arXiv:2403.03811v1 Announce Type: cross
Abstract: This work considers a repeated principal-agent bandit game, where the principal can only interact with her environment through the agent. The principal and the agent have misaligned objectives and the choice of action is only left to the agent. However, the principal can influence the agent's decisions by offering incentives which add up to his rewards. The principal aims to iteratively learn an incentive policy to maximize her own total utility. This framework extends usual …

abstract agent arxiv cs.gt cs.lg decisions environment game games her however influence stat.ml through type work