Relational reinforcement learning is presented, a learning technique that combines reinforcement learning with relational learning or inductive logic programming. Due to the use of a more expressive representation language to represent states, actions and Q-functions, relational reinforcement learning can be potentially applied to a new range of learning tasks. One such task that we investigate is planning in the blocks world, where it is assumed that the effects of the actions are unknown to the agent and the agent has to learn a policy. Within this simple domain we show that relational reinforcement learning solves some existing problems with reinforcement from specific goals pursued and to exploit the results of previous learning phases when addressing new (more complex) situations.

. One of the defining challenges for the KDD research community is to enable inductive learning algorithms to mine very large databases. This paper summarizes, categorizes, and compares existing work on scaling up inductive algorithms. We concentrate on algorithms that build decision trees and rule sets, in order to provide focus and specific details; the issues and techniques generalize to other types of data mining. We begin with a discussion of important issues related to scaling up. We highlight similarities among scaling techniques by categorizing them into three main approaches. For each approach, we then describe, compare, and contrast the different constituent techniques, drawing on specific examples from published papers. Finally, we use the preceding analysis to suggest how to proceed when dealing with a large problem, and where to focus future research. Keywords: scaling up, inductive learning, decision trees, rule learning 1. Introduction The knowledge discovery and data...

Inductive logic programming, or relational learning, is a powerful paradigm for machine learning or data mining. However, in order for ILP to become practically useful, the efficiency of ILP systems must improve substantially. To this end, the notion of a query pack is introduced: it structures sets of similar queries. Furthermore, a mechanism is described for executing such query packs. A complexity analysis shows that considerable efficiency improvements can be achieved through the use of this query pack execution mechanism. This claim is supported by empirical results obtained by incorporating support for query pack execution in two existing learning systems.

Most of today's structured data is stored in relational databases. Such a database consists of multiple relations which are linked together conceptually via entity-relationship links in the design of relational database schemas. Multi-relational classification can be widely used in many disciplines, such as financial decision making, medical research, and geographical applications. However, most classification approaches only work on single "flat" data relations. It is usually difficult to convert multiple relations into a single flat relation without either introducing huge, undesirable "universal relation" or losing essential information. Previous works using Inductive Logic Programming approaches (recently also known as Relational Mining) have proven effective with high accuracy in multi-relational classification. Unfortunately, they suffer from poor scalability w.r.t. the number of relations and the number of attributes in databases.

In a multiple-instance representation, each learning example is represented by a “bag” of fixed-length “feature vectors”. Such a representation, lying somewhere between propositional and first-order representation, offers a tradeoff between the two. This paper proposes a generic extension to propositional rule learners to handle multiple-instance data. It describes NAIVE-RIPPERMI, an implementation of this extension on the rule learning algorithm RIPPER. It then explains several pitfalls encountered by this naive extension during induction. It goes on to describe algorithmic modifications and a new multipleinstance coverage measure which are shown to avoid these pitfalls. Experimental results show the benefits of this approach for solving propositionalized relational problems in terms of speed and accuracy. keywords: Multiple-instance learning problem, rule learning, propositionalization, relational learning, mutagenesis learning task 1 1

Within KDD, the discovery of frequent patterns has been studied in a variety of settings. In its simplest form, known from association rule mining, the task is to discover all frequent item sets, i.e., all combinations of items that are found in a sufficient number of examples.

Inductive logic programming systems usually send large numbers of queries to a database. The lattice structure from which these queries are typically selected causes many of these queries to be highly similar. As a consequence, independent execution of all queries may involve a lot of redundant computation. We propose a mechanism for executing a hierarchically structured set of queries (a "query pack") through which a lot of redundancy in the computation is removed. We have incorporated our query pack execution mechanism in the ILP systems Tilde and Warmr by implementing a new Prolog engine ilProlog which provides support for pack execution at a lower level. Experimental results demonstrate significant efficiency gains. Our query pack execution mechanism is very general in nature and could be incorporated in most other ILP systems, with similar efficiency improvements to be expected.

Abstract not found

Knowledge discovery in spatial databases raises challenging multirelational data mining problems. A promising solution approach comes from the field of inductive logic programming (ILP). In this paper, an ILP method for spatial association rule mining is presented. It benefits from the available prior knowledge on the spatial domain, systematically explores the hierarchical structure of geographic layers, and deals with numerical aspatial properties of spatial objects. The method has been implemented into the ILP system SPADA which operates on a deductive relational database set up by an initial step of feature extraction from a spatial database. Advantages and limits of the method are illustrated by means of examples taken from an application of SPADA to the spatial data of an Italian province.

An important ingredient in agent-mediated Electronic Commerce is the presence of intelligent mediating agents that assist Electronic Commerce participants (e.g., individual users, other agents, organisations). These mediating agents are in principle autonomous agents that will interact with their environments (e.g. other agents and web-servers) on behalf of participants who have delegated tasks to them. For mediating agents a (preference) model of participants is indispensable. In this paper, a generic mediating agent architecture is introduced. Furthermore, we discuss our view of user preference modelling and its need in agent-mediated electronic commerce. We survey the state of the art in the field of preference modelling and suggest that the preferences of electronic commerce participants can be modelled by learning from their behaviour. In particular, we employ an existing machine learning method called inductive logic programming (ILP). We argue that this method can be used by mediating agents to detect regularities in the behaviour of the involved participants and induce hypotheses about their preferences automatically. Finally, we discuss some advantages and disadvantages of using inductive logic programming as a method for learning user preferences and compare this method with other approaches.