http://hdl.handle.net/10016/6650 Wed, 22 May 2013 12:21:07 GMT 2013-05-22T12:21:07Z http://hdl.handle.net/10016/16247 Title: An experience applying reinforcement learning in a web-based adaptive and intelligent educational system Author(s): Iglesias, Ana; Martínez, Paloma; Fernández, Fernando Abstract: The definition of effective pedagogical strategies for coaching and tutoring students according to their needs is one of the most important issues in Adaptive and Intelligent Educational Systems (AIES). The use of a Reinforcement Learning (RL) model allows the system to learn automatically how to teach to each student individually, only based on the acquired experience with other learners with similar characteristics, like a human tutor does. The application of this artificial intelligence technique, RL, avoids to define the teaching strategies by learning action policies that define what, when and how to teach. In this paper we study the performance of the RL model in a DataBase Design (DBD) AIES, where this performance is measured on number of students required to acquire efficient teaching strategies. Fri, 28 Feb 2003 23:00:00 GMT http://hdl.handle.net/10016/16247 2003-02-28T23:00:00Z http://hdl.handle.net/10016/13273 Title: Learning in Large Cooperative Multi-Robot Domains Author(s): Fernández, Fernando; Parker, Lynne E. Abstract: The development of mechanisms that enable robot teams to autonomously generate cooperative behaviours is one of the most interesting issues in dis- tributed and autonomous robotic systems. In this paper, the application of reinforcement learning techniques to robot teams is studied, enabling the robot to learn cooperative behaviours based only on local information. Sun, 31 Dec 2000 23:00:00 GMT http://hdl.handle.net/10016/13273 2000-12-31T23:00:00Z http://hdl.handle.net/10016/8289 Title: Integrating planning and scheduling in workflow domains Author(s): R-Moreno, María Dolores; Borrajo, Daniel; Cesta, Amedeo; Oddi, Angelo Abstract: One of the main obstacles in applying AI planning techniques to real problems is the difficulty to model the domains. Usually, this requires that people that have developed the planning system carry out the modeling phase since the representation depends very much on a deep knowledge of the internal working of the planning tools. On some domains such as business process reengineering (BPR), there has already been work on the definition of languages that allow non-experts entering knowledge on processes into the tools. We propose here the use of one of such BPR languages to enter knowledge on the organisation processes to be used by planning tools. Then, planning tools can be used to semi-automatically generate business process models. As instances of this domain, we will use the workflow modeling tool SHAMASH, where we have exploded its object oriented structure to introduce the knowledge through its user-friendly interface and, using a translator transform it into predicate logic terms. After this conversion, real models can be automatically generated using a planner that integrates planning and scheduling, IPSS. We present results in a real workflow domain, the telephone installation (TI) domain. Sun, 30 Sep 2007 22:00:00 GMT http://hdl.handle.net/10016/8289 2007-09-30T22:00:00Z http://hdl.handle.net/10016/8286 Title: PLTOOL: a knowledge engineering tool for planning and learning Author(s): Fernández, Susana; Borrajo, Daniel; Fuentetaja, Raquel; Arias, Juan D.; Veloso, Manuela Abstract: Artificial intelligence (AI) planning solves the problem of generating a correct and efficient ordered set of instantiated activities, from a knowledge base of generic actions, which when executed will transform some initial state into some desirable end-state. There is a long tradition of work in AI for developing planners that make use of heuristics that are shown to improve their performance in many real world and artificial domains. The developers of planners have chosen between two extremes when defining those heuristics. The domain-independent planners use domain-independent heuristics, which exploit information only from the ‘syntactic’ structure of the problem space and of the search tree. Therefore, they do not need any ‘semantic’ information from a given domain in order to guide the search. From a knowledge engineering (KE) perspective, the planners that use this type of heuristics have the advantage that the users of this technology need only focus on defining the domain theory and not on defining how to make the planner efficient (how to obtain ‘good’ solutions with the minimal computational resources). However, the domain-dependent planners require users to manually represent knowledge not only about the domain theory, but also about how to make the planner efficient. This approach has the advantage of using either better domain-theory formulations or using domain knowledge for defining the heuristics, thus potentially making them more efficient. However, the efficiency of these domain-dependent planners strongly relies on the KE and planning expertise of the user. When the user is an expert on these two types of knowledge, domain-dependent planners clearly outperform domain-independent planners in terms of number of solved problems and quality of solutions. Machine-learning (ML) techniques applied to solve the planning problems have focused on providing middle-ground solutions as compared to the aforementioned two extremes. Here, the user first defines a domain theory, and then executes the ML techniques that automatically modify or generate new knowledge with respect to both the domain theory and the heuristics. In this paper, we present our work on building a tool, PLTOOL (planning and learning tool), to help users interact with a set of ML techniques and planners. The goal is to provide a KE framework for mixed-initiative generation of efficient and good planning knowledge. Sun, 31 Dec 2006 23:00:00 GMT http://hdl.handle.net/10016/8286 2006-12-31T23:00:00Z