Incentive design for learning in user-recommendation systems with time-varying states
It provides a mechanism design for learning in sequential decision-making with asymmetric information, relevant for recommendation systems and decentralized control.
This paper addresses the challenge of incentivizing strategic users to truthfully reveal private signals in a user-recommendation system with time-varying states, achieving small gaps between strategic and team objectives with low expected incentive payments.
We consider the problem of how strategic users with asymmetric information can learn an underlying time varying state in a user-recommendation system. Users who observe private signals about the state, sequentially make a decision about buying a product whose value varies with time in an ergodic manner. We formulate the team problem as an instance of decentralized stochastic control problem and characterize its optimal policies. With strategic users, we design incentives such that users reveal their true private signals, so that the gap between the strategic and team objective is small and the overall expected incentive payments are also small.