Meta-Iearning of Bidding Agent with Knowledge Gradient in a Fully Agent-based Sponsored Search Auction Simulator: Extended Abstract

摘要

We take a practical approach on learning how to bid in sponsored search auctions, and model the problem of improving real world profit of advertisers in sponsored search auction as a meta-learning problem of configuring adaptive bidding agents. We construct a fully agent-based sponsored search auction simulator that 1) captures the dynamic nature of sponsored search auctions, 2) emulates the interface of Google AdWords platforms, and 3) can be customized and extended by modules. We then present Meta-LQKG algorithm, an agent-based meta-learning algorithm using knowledge gradient, and show the effect of meta-learning with Meta-LQKG on the performance of adaptive bidding agents.