Publication Date: January 1996
We consider the situation where a single consumer buys a stream of goods from diﬀerent sellers over time. The true value of each seller’s product to the buyer is initially unknown. Additional information can be gained only by experimentation. For exogenously given prices the buyer’s problem is a multi-armed bandit problem. The innovation in this paper is to endogenize the cost of experimentation to the consumer by allowing for price competition between the sellers. The role of prices is then to allocate intertemporally the costs and beneﬁts of learning between buyer and sellers. We examine how strategic aspects of the oligopoly model interact with the learning process.
All Markov Perfect Equilibria (MPE) are eﬀicient. We identify an equilibrium which besides its unique robustness properties has a strikingly simple, seemingly myopic pricing rule. Prices below marginal cost emerge naturally to sustain experimentation. Intertemporal exchange of the gains of learning is necessary to support eﬀicient experimentation. We analyze the asymptotic behavior of the equilibria.