|
|
Sun Labs Technical Report TR-2007-169
A Gradient-Based Reinforcement Learning Approach to Dynamic Pricing in Partially-Observable Environments
by David Vengerov
September 25, 2007 -
As more companies are beginning to adopt the e-business model, it becomes easier for buyers to compare prices at multiple sellers and choose the one that charges the best price for the same item or service. As a result, the demand for the goods of a particular seller is becoming more unstable, since other sellers are regularly offering discounts that attract large fractions of buyers. Therefore, it becomes more important for each seller to switch from static to dynamic pricing policies that take into account observable characteristics of the current demand and the state of the seller's resources.
This paper presents a Reinforcement Learning algorithm that can tune parameters of a seller's dynamic pricing policy in a gradient direction (thus maximizing the profit obtained with this policy) even when the seller's environment is not fully observable. A simulated Grid market was used to demonstrate a significant increase in profit that can be obtained by a Grid service provider if it adopts a dynamic pricing policy tuned by Reinforcement Learning.
|
