This paper discusses a system that accelerates reinforcement learning by using transfer from related tasks. Without such transfer, even if two tasks are very similar at some abstract level, an extensive re-learning eeort is required. The system achieves much of its power by transferring parts of previously learned solutions rather than a single complete solution. The system exploits strong feat...

In this paper, we describe research to improve Frito-Lay’s outbound supply chain activities by simultaneously optimizing its inventory and transportation decisions. Motivated by Frito-Lay’s practice, we first develop a mixed-integer programming formulation from which we develop a large-scale, integrated multiproduct inventory lot-sizing and vehicle-routing model with explicit (1) inventory hold...

high congestion of returned product at remanufacturing facility causes substantial delays and consequently remarketing value losses for time-sensitive and high-tech products with short life cycles, such as electronic equipments. at the remanufacturing site the returned product are inspected and classified according to their quality and processing time in one of the two classes: class 1 being ad...

In this paper, we use reinforcement learning (RL) techniques to determine dynamic prices in an electronic monopolistic retail market. The market that we consider consists of two natural segments of customers, captives and shoppers. Captives are mature, loyal buyers whereas the shoppers are more price sensitive and are attracted by sales promotions and volume discounts. The seller is the learnin...

This article introduces the notions of functional space and concept as a way of knowledge representation and abstraction for Reinforcement Learning agents. These definitions are used as a tool of knowledge transfer among agents. The agents are assumed to be heterogeneous; they have different state spaces but share a same dynamic, reward and action space. In other words, the agents are assumed t...

The key issue of inventory management is the problem of safety stock control. The existence of imprecise data makes this control complex. Fuzzy logic (FL) is widely used to develop expert system, due to its ability in representing imprecise data. Therefore, in this study a fuzzy logic system and theory have been used that incorporate the linguistic variable more practically and also help in eli...

Any system that learns how to lter documents will suuer poor performance during an initial training phase. One way of addressing this problem is to exploit lters learned by other users in a collaborative fashion. We investigate \direct transfer" of learned lters in this setting|a limiting case for any collab-orative learning system. We evaluate the stability of several diierent learning methods...

conclusions the findings of this study can be useful in competency development of health care management students. this approach paves the way towards effective and practical learning for these students to prepare them for opportunities in their future market job. background determination of the individual differences and students’ learning style are essential factors in the selection of proper...

Today, the effective inventory management plays an important role in the success of the organizations in the new business environment. It is not clearly possible for the organizations that store hundreds of inventory items to economically design an inventory management policy for each inventory item separately. Moreover, various inventory items may play quite different roles in the business ...

This paper presents a framework, called the knowledge co-creation framework (KCF), for heterogeneous multiagent robot systems that use a transfer learning method. A multiagent robot system (MARS) that utilizes reinforcement learning and a transfer learning method has recently been studied in realworld situations. In MARS, autonomous agents obtain behavior autonomously through multi-agent reinfo...