Using Cases Utility for Heuristic Planning Improvement

Borrajo

2010

Pattern Anal Applic

Self Cite

The main goal of Nearest Prototype Classification is to reduce storage space and retrieval time of classical Instance-Based Learning (IBL) algorithms. This motivation is higher in relational data since relational distance metrics are much more expensive to compute than classical distances like Euclidean distance. In this paper, we present an algorithm to build Relational Nearest Prototype Classifiers (RNPCs). When compared with Relational Instance-Based Learning (Relational IBL or RIBL) approaches, the algorithm is able to dramatically reduce the number of instances by selecting the most relevant prototypes, maintaining similar accuracy. The number of prototypes is obtained automatically by the algorithm, although it can also be bound by the user. In this work, we also show an application of RNPC for automated planning. Specifically, we describe a modeling task where a relational policy is built following an IBL approach. This approach uses the decisions taken by a planning system as learning examples. We show that when the number of learning examples is reduced with RNPC, the resulting policy is able to scale up better than the original planning system.

Section: Zenotravelmentioning

confidence: 99%

“…In all the planning tasks of this work, we have used the heuristic and forward search SAYPHI planner [25], which is a reimplementation of the METRIC-FF planner [26], currently one of the most efficient planners. The FF planner [27] introduces two concepts used in Sect.…”

Section: Automated Planningmentioning

confidence: 99%

A prototype-based method for classification with time constraints: a case study on automated planning

García-Durán

Borrajo

2010

Pattern Anal Applic

Self Cite

“…• Standard relational • Engineering effort to (Minton, 1988), classification algorithms integrate with different PRIAR (Kambhampati and Hendler, 1992), search algorithms and HAMLET (Borrajo and Veloso, 1997), domain-independent (Khardon, 1999), heuristics (Martin and Geffner, 2000), DISTILL (Winner and Veloso, 2003), OBTUSEWEDGE , CABALA (de la Rosa et al, 2007), ROLLER (de la Rosa et al, 2008) Generalized Heuristics…”

Section: Features Implementations Model Strengths Weaknessesmentioning

confidence: 99%

A review of machine learning for automated planning

Jiménez

Rosa

The Knowledge Engineering Review

et al. 2012

Self Cite

Recent discoveries in automated planning are broadening the scope of planners, from toy problems to real applications. However, applying automated planners to real-world problems is far from simple. On the one hand, the definition of accurate action models for planning is still a bottleneck. On the other hand, off-the-shelf planners fail to scale up and to provide good solutions in many domains. In these problematic domains, planners can exploit domain-specific control knowledge to improve their performance in terms of both speed and quality of the solutions. However, manual definition of control knowledge is quite difficult. This paper reviews recent techniques in machine learning for the automatic definition of planning knowledge. It has been organized according to the target of the learning process: automatic definition of planning action models and automatic definition of planning control knowledge. In addition, the paper reviews the advances in the related field of reinforcement learning.

“…It returns a set of plans in XML format ready for the conversion to a KFML format. Currently, planning tasks are solved by the sayphi planner (De la Rosa et al 2007), but the architecture could potentially use any other planner that supports fluents, conditional effects and metrics. We have used sayphi because it: i) supports an extensive subset of PDDL; and ii) incorporates several search algorithms Planning for Data Mining 5 able to deal with quality metrics, and generate several plans.…”

Section: Use Of Standard Languagesmentioning

confidence: 99%

Using automated planning for improving data mining processes

Rosa

The Knowledge Engineering Review

et al. 2013

Self Cite

This paper presents a distributed architecture for automating data mining processes using standard languages. Data mining is a difficult task that relies on an exploratory and analytic process of processing large quantities of data in order to discover meaningful patterns. The increasing heterogeneity and complexity of available data requires some expert knowledge on how to combine the multiple and alternative data mining tasks to process the data. Here, we describe data-mining tasks in terms of Automated Planning, which allows us to automate the data-mining knowledge flow construction. The work is based on the use of standards that have been defined in both data mining and automated-planning communities. Thus, we use PMML (Predictive Model Markup Language) to describe data mining tasks. From the PMML, a problem description in PDDL (Planning Domain Definition Language) can be generated, so any current planning system can be used to generate a plan. This plan is, again, translated to a data-mining workflow description, KFML format (Knowledge Flow file for the WEKA tool), so the plan or data-mining workflow can be executed in WEKA (Waikato Environment for Knowledge Analysis).