Vision-based Imitation Learning has achieved remarkable success in gripper manipulation, as ut eliminates the need for exhaustive programming. However, current methods depend on large, task-specific datasets or require replaying policies under identical training conditions, which limiting their scalability. Moreover, as grippers evolve into humanoid hands, the challenge of precise control grows substantially. In this paper, we propose a speech-driven controller for human-sized robotic hands that translates natural language commands directly into actuator controls, removing the need for task-specific video data and enabling a more natural human–robot interaction. To achieve this, we first train a model to map observed human hand motion to actuator controls through a camera. This learned model forms the foundation for rapidly developing a library of motion primitives. Subsequently, we train an Autoregressive Stateful Neural Network to convert verbal instructions into sequences of those primitives, composing multi-step trajectory sequences. We validate our approach by integrating the controller into the open-source InMoov Hand-i2 project. This work lays the groundwork for scalable, adaptable controllers that can be fine-tuned to new tasks with minimal effort. We provide the supplementary material and the code on Github: https://github.com/kochlisGit/InmoovNet.

Personality traits are essential for understanding human behavior, with applications in many areas such as job screening and team building. Traditional self-assessment methods are prone to biases and often mundane, leading to misleading results. To address these limitations, we propose MindEscape a novel game-based approach using a digital 3D Escape Room, and Artificial Intelligence-driven models, based on the OCEAN Five personality traits (openness, conscientiousness, extraversion, agreeableness, neuroticism). We developed a Multi-Output Regression System (MORS), which is used to make personality assessment to human players based on their gameplay data. As this AI model needs labeled data to be trained on, we developed single- and multi-agent systems that emulate human behaviors using custom reward functions powered by deep-Reinforcement Learning and generate the necessary data to train the system. Preliminary experiments with students from Greece and Italy show strong correlations between game-derived profiles and questionnaire baselines. This methodology offers an engaging, scalable and objective alternative for individual and team personality evaluation, advancing data-driven assessment methods.

Drug-Drug Interactions (DDI) identification is a part of the drug safety process, that focuses at avoiding potential adverse drug effects that can lead to patient health risks. With the exponential growth in published literature, it becomes increasingly difficult to extract useful information from the most relevant research. Therefore, Machine Learning and specifically Relationship Extraction has been employed for the extraction of DDIs from biomedical literature. This task consists of both Named Entity Recognition and Relationship Classification techniques tackled in either pipelined or joint approaches for recognizing drug mentions and classifying their interactions, respectively. However, current approaches are prone to error propagation between the tasks, not taking the relevance between them into account. In this paper we propose TransformDDI, an end-to-end Transformer-based joint multi-task DDI extraction model that integrates domain knowledge and a shared parameter layer in a dynamic drug entities extraction and interaction classification Language Model architecture. Our proposed model can generate variable outputs based on the recognized drug entities in a single-model architecture by implementing a Dynamic Pair Attention Mechanism with task-specific focus and dynamic loss functions. Experiments conducted on the DDI Extraction 2013 benchmark corpus indicate that our methodology offers significant improvements over the current state-of-the-art.

Abstract Cryptocurrency markets experienced a significant increase in the popularity, which motivated many financial traders to seek high profits in cryptocurrency trading. The predominant tool that traders use to identify profitable opportunities is technical analysis. Some investors and researchers also combined technical analysis with machine learning, in order to forecast upcoming trends in the market. However, even with the use of these methods, developing successful trading strategies is still regarded as an extremely challenging task. Recently, deep reinforcement learning (DRL) algorithms demonstrated satisfying performance in solving complicated problems, including the formulation of profitable trading strategies. While some DRL techniques have been successful in increasing profit and loss (PNL) measures, these techniques are not much risk-aware and present difficulty in maximizing PNL and lowering trading risks simultaneously. This research proposes the combination of DRL approaches with rule-based safety mechanisms to both maximize PNL returns and minimize trading risk. First, a DRL agent is trained to maximize PNL returns, using a novel reward function. Then, during the exploitation phase, a rule-based mechanism is deployed to prevent uncertain actions from being executed. Finally, another novel safety mechanism is proposed, which considers the actions of a more conservatively trained agent, in order to identify high-risk trading periods and avoid trading. Our experiments on 5 popular cryptocurrencies show that the integration of these three methods achieves very promising results.

Complex games require disparate behaviors in order to be solved, giving space to researchers to study AI model behaviors in various settings. At the same time, the video game industry benefits by incorporating these models in their games for delivering realistic and challenging gameplay experience to users. However, there is a well-known difficulty of implementing and training efficient models in complex games for entertainment purposes. In this paper, we report on our approach to overcome this challenge and ultimately develop AlphaBluff, a Heads-Up No-Limit Texas Hold’em (HUNL) Poker variation video game developed in the Unity game engine, in which human players can play against trained AI opponents. Initially we trained different state-of-the-art AI models and analyzed their individual performance scores in a custom HUNL environment, as well as their performance against each other. AlphaBluff was developed with the goal of producing a professional-level poker video game that includes cutting-edge AI opponents, which, to our knowledge has never been developed before. Using data gathered by gameplay sessions from beta testers, we performed a statistical analysis and concluded that our models have a high win rate against human players. An adaptation of our system can further enrich this unique gameplay experience by combining these models, data and statistical reports, in order to develop an efficient player-opponent matchmaking mechanism.

Multi-target regression is concerned with the prediction of multiple continuous target variables using a shared set of predictors. Two key challenges in multi-target regression are: (a) modelling target dependencies and (b) scalability to large output spaces. In this paper, a new multi-target regression method is proposed that tries to jointly address these challenges via a novel problem transformation approach. The proposed method, called MRQ, is based on the idea of quantizing the output space in order to transform the multiple continuous targets into one or more discrete ones. Learning on the transformed output space naturally enables modeling of target dependencies while the quantization strategy can be flexibly parameterized to control the trade-off between prediction accuracy and computational efficiency. Experiments on a large collection of benchmark datasets show that MRQ is both highly scalable and also competitive with the state-of-the-art in terms of accuracy. In particular, an ensemble version of MRQ obtains the best overall accuracy, while being an order of magnitude faster than the runner up method.

Deep Reinforcement Learning is a topic that has gained a lot of attention recently, due to the unprecedented achievements and remarkable performance of such algorithms in various benchmark tests and environmental setups. The power of such methods comes from the combination of an already established and strong field of Deep Learning, with the unique nature of Reinforcement Learning methods. It is, however, deemed necessary to provide a compact, accurate and comparable view of these methods and their results for the means of gaining valuable technical and practical insights. In this work we gather the essential methods related to Deep Reinforcement Learning, extracting common property structures for three complementary core categories: a) Model-Free, b) Model-Based and c) Modular algorithms. For each category, we present, analyze and compare state-of-the-art Deep Reinforcement Learning algorithms that achieve high performance in various environments and tackle challenging problems in complex and demanding tasks. In order to give a compact and practical overview of their differences, we present comprehensive comparison figures and tables, produced by reported performances of the algorithms under two popular simulation platforms: the Atari Learning Environment and the MuJoCo physics simulation platform. We discuss the key differences of the various kinds of algorithms, indicate their potential and limitations, as well as provide insights to researchers regarding future directions of the field.

BACKGROUND: Somatic Hypermutation (SHM) refers to the introduction of mutations within rearranged V(D)J genes, a process that increases the diversity of Immunoglobulins (IGs). The analysis of SHM has offered critical insight into the physiology and pathology of B cells, leading to strong prognostication markers for clinical outcome in chronic lymphocytic leukaemia (CLL), the most frequent adult B-cell malignancy. In this paper we present a methodology for integrating multiple immunogenetic and clinocobiological data sources in order to extract features and create high quality datasets for SHM analysis in IG receptors of CLL patients. This dataset is used as the basis for a higher level integration procedure, inspired form social choice theory. This is applied in the Towards Analysis, our attempt to investigate the potential ontogenetic transformation of genes belonging to specific stereotyped CLL subsets towards other genes or gene families, through SHM. RESULTS: The data integration process, followed by feature extraction, resulted in the generation of a dataset containing information about mutations occurring through SHM. The Towards analysis performed on the integrated dataset applying voting techniques, revealed the distinct behaviour of subset #201 compared to other subsets, as regards SHM related movements among gene clans, both in allele-conserved and non-conserved gene areas. With respect to movement between genes, a high percentage movement towards pseudo genes was found in all CLL subsets. CONCLUSIONS: This data integration and feature extraction process can set the basis for exploratory analysis or a fully automated computational data mining approach on many as yet unanswered, clinically relevant biological questions.

This work aims to advance Web Service retrieval, also known as Matching, in two directions. First, it introduces a matching algorithm for SAWSDL, which adapts and extends known concepts with novel strategies. Effective logic-based and syntactic strategies are introduced and combined in a novel hybrid strategy, targeting an envisioned well-defined, real-world scenario for matching. The algorithm is evaluated in a universal environment for matching algorithms, SME2, in an objective, reproducible manner. Evaluation ranks Tomaco high amongst state of the art, especially for early recall levels (first in macro-averaging precision, up to 0.7 recall). Secondly, this work introduces the Tomaco web application, which aims to promote wide-spread adoption of Semantic Web Services while targeting the lack of user-friendly applications in this field, by integrating a variety of configurable matching algorithms proposed in this paper. It, finally, allows discovery of both existing and user-contributed service collections and ontologies, serving also as a service registry.

Results returned by commercial image search engines should include relevant and diversified depictions of queries in order to ensure good coverage of users' information needs. While relevance has drastically improved in recent years, diversity is still an open problem. In this paper we propose a reranking method that could be implemented on top of such engines in order to provide a better balance between relevance and diversity. Our method formulates the reranking problem as an optimization of a utility function that jointly considers relevance and diversity. Our main contribution is the replacement of the unsupervised definition of relevance that is commonly used in this formulation with a supervised classification model that strives to capture a query and application-specific notion of relevance. This model provides more accurate relevance scores that lead to significantly improved diversification performance. Furthermore, we propose a stacking-type ensemble learning approach that allows combining multiple features in a principled way when computing the relevance of an image. An empirical evaluation carried out on the datasets of the MediaEval 2013 and 2014 "Retrieving Diverse Social Images" (RDSI) benchmarks confirms the superior performance of the proposed method compared to other participating systems as well as a state-of-the-art, unsupervised reranking method.

This article introduces a teacher–student framework for reinforcement learning, synthesising and extending material that appeared in conference proceedings [Torrey, L., & Taylor, M. E. (2013)]. Teaching on a budget: Agents advising agents in reinforcement learning. {Proceedings of the international conference on autonomous agents and multiagent systems}] and in a non-archival workshop paper [Carboni, N., &Taylor, M. E. (2013, May)]. Preliminary results for 1 vs. 1 tactics in StarCraft. {Proceedings of the adaptive and learning agents workshop (at AAMAS-13)}]. In this framework, a teacher agent instructs a student agent by suggesting actions the student should take as it learns. However, the teacher may only give such advice a limited number of times. We present several novel algorithms that teachers can use to budget their advice effectively, and we evaluate them in two complex video games: StarCraft and Pac-Man. Our results show that the same amount of advice, given at different moments, can have different effects on student learning, and that teachers can significantly affect student learning even when students use different learning methods and state representations.

This paper deals with content-based large-scale image retrieval using the state-of-the-art framework of VLAD and Product Quantization proposed by Jegou as a starting point. Demonstrating an excellent accuracy-efficiency trade-off, this framework has attracted increased attention from the community and numerous extensions have been proposed. In this work, we make an in-depth analysis of the framework that aims at increasing our understanding of its different processing steps and boosting its overall performance. Our analysis involves the evaluation of numerous extensions (both existing and novel) as well as the study of the effects of several unexplored parameters. We specifically focus on: a) employing more efficient and discriminative local features; b) improving the quality of the aggregated representation; and c) optimizing the indexing scheme. Our thorough experimental evaluation provides new insights into extensions that consistently contribute, and others that do not, to performance improvement, and sheds light onto the effects of previously unexplored parameters of the framework. As a result, we develop an enhanced framework that significantly outperforms the previous best reported accuracy results on standard benchmarks and is more efficient.

The present work demonstrates a novel, free and open-source educational software package on wireless communications. Targeting graduate and post-graduate studies, the package covers issues of antennas and propagation, wireless channel modeling (fading, shadowing, path loss, Doppler effect), static and adaptive modulation, client mobility and network planning applied to DVB/T and indoor networks (WiFi, femtocell) settings. The corresponding packages are fully interactive and parametric, offering 3D GUIs, ray traced maps and connection to field measurements. Being extensible via the addition of simple text files, the presented package constitutes a concrete approach that was missing from the related approaches that follow the virtual laboratories paradigm.

The paper presents an integrated approach for automated semantic web service composition using AI planning techniques. An important advantage of this approach is that the composition process, as well as the discovery of the atomic services that take part in the composition, are significantly facilitated by the incorporation of semantic information. OWL-S web service descriptions are transformed into a planning problem described in a standardized fashion using PDDL, while semantic information is used for the enhancement of the composition process as well as for approximating the optimal composite service when exact solutions are not found. Solving, visualization, manipulation, and evaluation of the produced composite services are accomplished, while, unlike other systems, independence from specific planners is maintained. Implementation was performed through the development and integration of two software systems, namely PORSCE II and VLEPPO. PORSCE II is responsible for the transformation process, semantic enhancement, and management of the results. VLEPPO is a general-purpose planning system used to automatically acquire solutions for the problem by invoking external planners. A case study is also presented to demonstrate the functionality, performance, and potential of the approach.

A simple yet effective multilabel learning method, called label powerset (LP), considers each distinct combination of labels that exist in the training set as a different class value of a single-label classification task. The computational efficiency and predictive performance of LP is challenged by application domains with large number of labels and training examples. In these cases, the number of classes may become very large and at the same time many classes are associated with very few training examples. To deal with these problems, this paper proposes breaking the initial set of labels into a number of small random subsets, called labelsets and employing LP to train a corresponding classifier. The labelsets can be either disjoint or overlapping depending on which of two strategies is used to construct them. The proposed method is called RAkEL (RAndom k labELsets), where k is a parameter that specifies the size of the subsets. Empirical evidence indicates that RAkEL manages to improve substantially over LP, especially in domains with large number of labels and exhibits competitive performance against other high-performing multilabel learning methods.

Multi-label classification is a popular learning task. However, some of the algorithms that learn from multi-label data, can only output a score for each label, so they cannot be readily used in applications that require bipartitions. In addition, several of the recent state-of-the-art multi-label classification algorithms, actually output a score vector primarily and employ one (sometimes simple) thresholding method in order to be able to output bipartitions. Furthermore, some approaches can naturally output both a score vector and a bipartition, but whether a better bipartition can be obtained through thresholding has not been investigated. This paper contributes a theoretical and empirical comparative study of existing thresholding methods, highlighting their importance for obtaining bipartitions of high quality.

Ensemble pruning is concerned with the reduction of the size of an ensemble prior to its combination. Its purpose is to reduce the space and time complexity of the ensemble and/or to increase the ensemble's accuracy. This paper focuses on instance-based approaches to ensemble pruning, where a different subset of the ensemble may be used for each different unclassified instance. We propose modeling this task as a multi-label learning problem, in order to take advantage of the recent advances in this area for the construction of effective ensemble pruning approaches. Results comparing the proposed framework against a variety of other instance-based ensemble pruning approaches in a variety of datasets using a heterogeneous ensemble of 200 classifiers, show that it leads to improved accuracy.

This paper presents PORSCE II, a system that combines planning and ontology concept relevance for automatically composing semantic web services. The presented approach includes transformation of the web service composition problem into a planning problem, enhancement with semantic awareness and relaxation and solution through external planners. The produced plans are visualized and their accuracy is assessed.

This paper presents a study on polyadenylation site prediction in mRNA sequences. We describe a method, called PolyA-EP, that we developed for predicting polyadenylation sites and we present a systematic study of the problem of recognizing mRNA 3' ends which contain a polyadenylation site using the proposed method. PolyA-EP exploits the advantages of emerging patterns, namely high understandability and discriminating power and can be used for both descriptive and predictive analysis. In particular, PolyA-EP is a parameterizable tool that can be used in order to extract interesting emerging patterns for describing or predicting polyadenylation sites. Moreover, the extracted emerging patterns can span across many elements around the polyadenylation site. We discuss the results of the experiments we conducted with Arabidopsis thaliana sequences drawing important conclusions and finally we propose a framework that improves the accuracy of polyadenylation site prediction.

This paper proposes a general framework for classifying data streams by exploiting incremental clustering in order to dynamically build and update an ensemble of incremental classifiers. To achieve this, a transformation function that maps batches of examples into a new conceptual feature space is proposed. The clustering algorithm is then applied in order to group different concepts and identify recurring contexts. The ensemble is produced by maintaining an classifier for every concept discovered in the streamThe full version of this paper as well as the datasets used for evaluation can be found at: http://mlkd.csd.auth.gr/concept_drift.html

Focused crawlers are programs that wander in the Web, using its graph structure, and gather pages that belong to a specific topic. The most critical task in Focused Crawling is the scoring of the URLs as it designates the path that the crawler will follow, and thus its effectiveness. In this paper we propose a novel scheme for assigning scores to the URLs, based on the Reinforcement Learning (RL) framework. The proposed approach learns to select the best classifier for ordering the URLs. This formulation reduces the size of the search space for the RL method and makes the problem tractable. We evaluate the proposed approach on-line on a number of topics, which offers a realistic view of its performance, comparing it also with a RL method and a simple but effective classifier-based crawler. The results demonstrate the strength of the proposed approach.

Ensemble selection deals with the reduction of an ensemble of predictive models in order to improve its efficiency and predictive performance. A number of ensemble selection methods that are based on greedy search of the space of all possible ensemble subsets have recently been proposed. This paper contributes a novel method, based on a new diversity measure that takes into account the strength of the decision of the current ensemble. Experimental comparison of the proposed method, dubbed Focused Ensemble Selection (FES), against state-of-the-art greedy ensemble selection methods shows that it leads to small ensembles with high predictive performance.

Multiagent learning attracts much attention in the past few years as it poses very challenging problems. Reinforcement Learning is an appealing solution to the problems that arise to Multi Agent Systems (MASs). This is due to the fact that Reinforcement Learning is a robust and well suited technique for learning in MASs. This paper proposes a multi-agent Reinforcement Learning approach, that uses coordinated actions, which we call strategies and a voting process that combines the decisions of the agents, in order to follow a strategy. We performed experiments to the predator-prey domain, comparing our approach with other multi-agent Reinforcement Learning techniques, getting promising results.

In this paper we present a method for classifying accurately SAGE (serial analysis of gene expression) data. The high dimensionality of the data, namely the large number of features, in combination with the small number of samples poses a great challenge and demands more accurate and robust algorithms for classification. The prediction accuracy of the up to now proposed approaches is moderate. In our approach we exploit the associations among the expressions of genes in order to construct more accurate classifiers. For validating the effectiveness of our approach we experimented with two real datasets using numerous feature selection and classification algorithms. The results have shown that our approach improves significantly the classification accuracy, which reaches 99%.

Abstract: In this paper we present an expert system that monitors seawater quality and pollution in northern Greece through a sensor network called Andromeda. The expert system monitors sensor data collected by local monitoring stations and reasons about the current level of water suitability for various aquatic uses, such as swimming and piscicultures. The aim of the expert system is to help the authorities in the decision‐making process in the battle against pollution of the aquatic environment, which is vital for public health and the economy of northern Greece. The expert system determines, using fuzzy logic, when certain environmental parameters exceed certain pollution limits, which are specified either by the authorities or by environmental scientists, and flags up appropriate alerts.

In this paper we apply a machine learning approach to the problem of estimating the number of defects called Regression via Classification (RvC). RvC initially automatically discretizes the number of defects into a number of fault classes, then learns a model that predicts the fault class of a software system. Finally, RvC transforms the class output of the model back into a numeric prediction. This approach includes uncertainty in the models because apart from a certain number of faults, it also outputs an associated interval of values, within which this estimate lies, with a certain confidence. To evaluate this approach we perform a comparative experimental study of the effectiveness of several machine learning algorithms in a software dataset. The data was collected by Pekka Forselious and involves applications maintained by a bank of Finland.

Defeasible reasoning is a rule-based approach for efficient reasoning with incomplete and inconsistent information. Such reasoning is, among others, useful for ontology integration, where conflicting information arises naturally; and for the modeling of business rules and policies, where rules with exceptions are often used. This paper describes these scenarios and reports on the implementation of a system for defeasible reasoning on the Web. The system, DR-DEVICE, is capable of reasoning about RDF metadata over multiple Web sources using defeasible logic rules. It is implemented on top of CLIPS production rule system and builds upon R-DEVICE, an earlier deductive rule system over RDF metadata that also supports derived attribute and aggregate attribute rules. Rules can be expressed either in a native CLIPS-like language, or in an extension of the OO-RuleML syntax. The operational semantics of defeasible logic are implemented through compilation into the generic rule language of R-DEVICE. The paper also presents a full semantic Web broker example for apartment renting.

In this paper we present R-DEVICE, a deductive object-oriented knowledge base system for reasoning over RDF metadata. R-DEVICE imports RDF documents into the CLIPS production rule system by transforming RDF triples into COOL objects and uses a deductive rule language for reasoning about them. R-DEVICE is based on an OO RDF data model, different than the established triple-based model, which maps resources to objects and encapsulates properties inside resource objects, as traditional OO attributes. In this way, fewer joins are required to access the properties of a single resource resulting in better inferencing/querying performance, as it is experimentally shown in the paper. Furthermore, RDF can interoperate seamlessly with other Web data models and languages. The descriptive semantics of RDF may call for dynamic redefinitions of resource classes, which are handled by R-DEVICE effectively. Furthermore, R-DEVICE features a powerful deductive rule language for reasoning on top of RDF metadata. The rule language includes features such as normal and generalized path expressions, stratified negation, aggregate, grouping, and sorting functions. The rule language supports a second-order syntax, which is efficiently translated into sets of first-order logic rules using metadata, where variables can range over classes and properties, so that reasoning over the RDF schema can be made. Users can define views that are materialized and incrementally maintained by translating deductive rules into CLIPS production rules that preserve truth. Users can choose between an OPS5/CLIPS-like and a RuleML-like syntax. Finally, users can define and use functions through the CLIPS host language.

One of the most promising trends in Domain-Independent AI Planning, nowadays, is state-space heuristic planning. The planners of this category construct general but efficient heuristic functions, which are used as a guide to traverse the state space either in a forward or in a backward direction. Although specific problems may favor one or the other direction, there is no clear evidence why any of them should be generally preferred. This paper presents Hybrid-AcE, a domain-independent planning system that combines search in both directions utilizing a complex criterion that monitors the progress of the search, to switch between them. Hybrid AcE embodies two powerful domain-independent heuristic functions extending one of the AcE planning systems. Moreover, the system is equipped with a fact-ordering technique and two methods for problem simplification that limit the search space and guide the algorithm to the most promising states. The bi-directional system has been tested on a variety of problems adopted from the AIPS planning competitions with quite promising results.

Distributed constraint satisfaction has drawn much attention in the past years, with a number of algorithms proposed to tackle the problem. Research in the area has followed two directions: distributed search techniques and distributed filtering techniques. This paper presents a new distributed filtering algorithm, named Distributed Singleton Arc Consistency (Dis-SAC), which is based on the singleton consistency algorithm. Dis-SAC is a parallel, coarse-grain filtering algorithm aimed at improving the performance of singleton consistency by distributing the work to be done to a number of agents. The current paper presents the basic idea behind the algorithm and two versions of it that employ different communication policies along with experimental results obtained on a set of random binary CSP problems.

This paper describes the integration of a multidatabase system and a knowledge-base system to support the data-integration component of a data warehouse. The multidatabase system integrates various component databases with a common query language; however, it does not provide capability for schema integration and other utilities necessary for data warehousing. In addition, the knowledge base system offers a declarative logic language with second-order syntax but first-order semantics for integrating the schemes of the data sources into the warehouse and for defining complex, recursively defined materialized views. Furthermore, deductive rules are also used for cleaning, checking the integrity and summarizing the data imported into the data warehouse. The knowledge base system features an efficient incremental view maintenance mechanism that is used for refreshing the data warehouse, without querying the data sources.

This paper presents GRT, a domain-independent heuristic planning system for STRIPS worlds. GRT solves problems in two phases. In the pre-processing phase, it estimates the distance between each fact and the goals of the problem, in a backward direction. Then, in the search phase, these estimates are used in order to further estimate the distance between each intermediate state and the goals, guiding so the search process in a forward direction and on a best-first basis. The paper presents the benefits from the adoption of opposite directions between the preprocessing and the search phases, discusses some difficulties that arise in the pre-processing phase and introduces techniques to cope with them. Moreover, it presents several methods of improving the efficiency of the heuristic, by enriching the representation and by reducing the size of the problem. Finally, a method of overcoming local optimal states, based on domain axioms, is proposed. According to it, difficult problems are decomposed into easier sub-problems that have to be solved sequentially. The performance results from various domains, including those of the recent planning competitions, show that GRT is among the fastest planners.

This paper describes Operator Distribution Method for parallel Planning (ODMP), a parallelization method for efficient heuristic planning. The method innovates in that it parallelizes the application of the available operators to the current state and the evaluation of the successor states using the heuristic function. In order to achieve better load balancing and a lift in the scalability of the algorithm, the operator set is initially enlarged, by grounding the first argument of each operator. Additional load balancing is achieved through the reordering of the operator set, based on the expected amount of imposed work. ODMP is effective for heuristic planners, but it can be applied to planners that embody other search strategies as well. It has been applied to GRT, a domain-independent heuristic planner, and CL, a heuristic planner for simple logistics problems, and has been thoroughly tested on a set of logistics problems adopted from the AIPS-98 planning competition, giving quite promising results.

This paper describes E-DEVICE, an extensible active knowledge base system (KBS) that supports the processing of event-driven, production, and deductive rules into the same active OODB system. E-DEVICE provides the infrastructure for the smooth integration of various declarative rule types, such as production and deductive rules, into an active OODB system that supports low-level event-driven rules only by: (1) mapping each declarative rule into one event-driven rule, offering centralized rule selection control for correct run-time behavior and conflict resolution, and (2) using complex events to map the conditions of declarative rules and monitor the database to incrementally match those conditions. E-DEVICE provides the infrastructure for easily extending the system by adding: (1) new rule types as subtypes of existing ones, and (2) transparent optimizations to the rule matching network. The resulting system is a flexible, yet efficient, KBS that gives the user the ability to express knowledge in a variety of high-level forms for advanced problem solving in data intensive applications.