In this paper we propose a novel multiagent learning approach, which is based on online analytical processing (OLAP) data mining. First, we describe a data cube OLAP architecture which facilitates effective storage and processing of the state information reported by agents. This way, the action of the other agent, even not in the visual environment of the agent under consideration, can simply be estimated by extracting online association rules from the constructed data cube. Then, we present a new action selection model which is also based on association rules mining. Finally, we generalize states which are not experienced sufficiently by mining multiple-levels association rules from the proposed data cube. Experiments conducted on a well-known pursuit domain show the effectiveness of the proposed learning approach.