In order to enable robots to interact with humans in a natural way, they need to be able to autonomously learn new tasks. The most natural way for humans to tell another agent, which can be a human or robot, to perform a task is via natural language. Thus, natural human–robot interactions also require robots to understand natural language, i.e. extract the meaning of words and phrases. To do this, words and phrases need to be linked to their corresponding percepts through grounding. Afterward, agents can learn the optimal micro-action patterns to reach the goal states of the desired tasks. Most previous studies investigated only learning of actions or grounding of words, but not both. Additionally, they often used only a small set of tasks as well as very short and unnaturally simplified utterances. In this paper, we introduce a framework that uses reinforcement learning to learn actions for several tasks and cross-situational learning to ground actions, object shapes and colors, and prepositions. The proposed framework is evaluated through a simulated interaction experiment between a human tutor and a robot. The results show that the employed framework can be used for both action learning and grounding.

An important aspect of any interactive computer system is its ease of use. On-line assistance is a major contributor to software usability. Conventional on-line assistance includes on-line documentation, or keyword access to textual help descriptions. More sophisticated on-line assistance includes intelligent help which provides immediate assistance for a specific problem, and intelligent training whose main goal is to support the user in learning about the system. These contemporary forms of intelligent assistance represent knowledge about the particular application, the user and the particular tasks the user is to perform. In addition, they possess inferencing capabilities to model the individual user's goals, plans, intentions and knowledge. This paper provides an overview of on-line assistance research, from empirical studies that attempt to determine the nature of effective assistance, to the design of intelligent on-line assistance systems capable of tailoring the assistance to the individual user. For readers interested in more details, recommendations for further reading in the related areas of advice-giving and intelligent help, intelligent user interfaces, critiquing, intelligent tutoring systems, and on-line documentation and hypertext are given.

This paper presents an approach for the enactment of policies in digital health based on our earlier work on the implementation of digital contracts in distributed systems. A formal policy model and an abstract policy language for the expression of healthcare policies are first proposed, leveraging the semantics of the ISO Reference Model for Open Distributed Processing enterprise language standard. Healthcare consent policies included in the HL7 Fast Health Interoperability Resource (FHIR®) standard are used to illustrate the modelling approach. Several distributed ledger and smart legal contract options were considered next as target platforms for implementation. Their benefits are highlighted along with considerations on their use reflecting business concerns of risk, trust and cost.

A humanoid robot developed to play multievent athletes like human has paved a way for interesting and popular robotics research. One of the great dreams is to develop a humanoid robot being able to challenge human athletes. Therefore, the challenge of humanoid robots to play archery against human is organized at Taichung, Taiwan, in HuroCup, FIRA 2018, on August 7th. The difficulties of developing humanoid robot are not just on playing archery. The humanoid robots for HuroCup must make use of the same hardware for the 10 events. In this paper, the design and implementation of the humanoid robot for archery are proposed under the trade off with other nine events. Therefore, the humanoid robot must have some special design and development on software. More specially, the humanoid robot must use professional bow to challenge human for archery competition. Therefore, in this paper, special shooting posture under constrained arm structure and motion planning of both arms for more torque to play professional bow are proposed. In addition, the further development of humanoid robot to improve archery shooting is summarized.

Multi-agent systems (MASs) are a form of distributed intelligence, where multiple autonomous agents act in a common environment. Numerous complex, real world systems have been successfully optimized using multi-agent reinforcement learning (MARL) in conjunction with the MAS framework. In MARL agents learn by maximizing a scalar reward signal from the environment, and thus the design of the reward function directly affects the policies learned. In this work, we address the issue of appropriate multi-agent credit assignment in stochastic resource management games. We propose two new stochastic games to serve as testbeds for MARL research into resource management problems: the tragic commons domain and the shepherd problem domain. Our empirical work evaluates the performance of two commonly used reward shaping techniques: potential-based reward shaping and difference rewards. Experimental results demonstrate that systems using appropriate reward shaping techniques for multi-agent credit assignment can achieve near-optimal performance in stochastic resource management games, outperforming systems learning using unshaped local or global evaluations. We also present the first empirical investigations into the effect of expressing the same heuristic knowledge in state- or action-based formats, therefore developing insights into the design of multi-agent potential functions that will inform future work.

Algorithmic bias arises in machine learning when models that may have reasonable overall accuracy are biased in favor of ‘good’ outcomes for one side of a sensitive category, for example gender or race. The bias will manifest as an underestimation of good outcomes for the under-represented minority. In a sense, we should not be surprised that a model might be biased when it has not been ‘asked’ not to be; reasonable accuracy can be achieved by ignoring the under-represented minority. A common strategy to address this issue is to include fairness as a component in the learning objective. In this paper, we consider including fairness as an additional criterion in model training and propose a multi-objective optimization strategy using Pareto Simulated Annealing that optimizes for both accuracy and underestimation bias. Our experiments show that this strategy can identify families of models with members representing different accuracy/fairness tradeoffs. We demonstrate the effectiveness of this strategy on two synthetic and two real-world datasets.

The aim of this commentary is to discuss the contribution of soft computing—a consortium of fuzzy logic, neural network theory, evolutionary computing, and probabilistic reasoning—to the development of case-based reasoning (CBR) systems. We will describe how soft computing has been used in case representation, retrieval, adaptation, reuse, and case-base maintenance, and then present a brief summary of six CBR applications that use soft computing techniques.

Often, the problems encountered by applications and developments of software agents require further investigation and improvements of agents' social capacities, that is, of the properties enabling them to act adaptively in multiagent domains. This is so for at least three reasons. First, quite often software agents are designed for reasoning upon and interacting with other agents (both human and artificial), as is the case in client-server and personal assistants. Secondly, to accomplish their primary task, these systems ought to reason upon, predict and eventually coordinate with, or at least prevent obstacles from, other systems accomplishing the same or different tasks in a concurrent way (think of electronic commerce, meeting agents, etc.). Thirdly, many applications are actually distributed over a set of agents with their specific roles and tasks, which are expected to participate in a joint activity, aimed at achieving a given global outcome.

Individual Evolutionary Learning (IEL) is a learning model based on the evolution of a population of strategies of an individual agent. In prior work, IEL has been shown to be consistent with the behavior of human subjects in games with a small number of agents. In this paper, we examine the performance of IEL in games with many agents. We find IEL to be robust to this type of scaling. With the appropriate linear adjustment of the mechanism parameter, the convergence behavior of IEL in games induced by Groves–Ledyard mechanisms in quadratic environments is independent of the number of participants.

In this paper we present our experience of representing the knowledge behind HealthAgents (HA), a distributed decision support system for brain tumour diagnosis. Our initial motivation came from the distributed nature of the information involved in the system and has been enriched by clinicians’ requirements and data access restrictions. We present in detail the steps we have taken towards building our ontology starting from knowledge acquisition to data access and reasoning. We motivate our representational choices and show our results using domain examples used by clinical partners in HA.

Matching algorithms automatically discover semantic relations between two autonomously developed conceptual representations of two overlapping domains. Typical examples of such conceptualisations are electronic market catalogues (e.g., unspsc and eCl@ss) and Web directories (e.g., google and yahoo). The objective of this paper is the description of a use case in which the matching algorithm CtxMatch, developed at ITC-IRST and the University of Trento, has been used to re-classify into the Universal Standard Products and Services Classification (unspsc) the catalogue of office equipment and accessories used by a worldwide telecommunication company to classify its suppliers. On the basis of this experience we are envisaging new applications of the algorithm in the area of demand aggregation. We conclude the paper by briefly describing a future application in this area.

Spreadsheets are a widespread tool for a variety of tasks, particularly in business settings. Spreadsheet users employ a form of programming that, although popular, is highly error-prone and has limited expressiveness. A promising approach to overcome these shortcomings is to augment spreadsheets with logic-based knowledge representation and reasoning (KR&R) functionality. In this paper, we present Logic Embedded in SpreadSheets (LESS), a system which integrates PowerLoom, a highly expressive logic-based KR&R system, with Microsoft (MS) Excel. The design of LESS provides different tiers of functionality that explore trade-offs between direct access to the underlying logic engine and user-friendly support for spreadsheets users. A prototype of LESS was implemented as an MS Excel add-in.

Currently, a large amount of spatial and spatiotemporal RDF data has been shared and exchanged on the Internet and various applications. Resource Description Framework (RDF) is widely accepted for representing and processing data in different (including spatiotemporal) application domains. The effective management of spatial and spatiotemporal RDF data are becoming more and more important. A lot of work has been done to study how to represent, query, store, and manage spatial and spatiotemporal RDF data. In order to grasp and learn the main ideas and research results of spatial and spatiotemporal RDF data, in this paper, we provide a comprehensive overview of RDF for spatial and spatiotemporal data management. We summarize spatial and spatiotemporal RDF data management from several essential aspects such as representation, querying, storage, performance assessment, datasets, and management tools. In addition, the direction of future research and some comparisons and analysis are also discussed in depth.

In the reinforcement learning context, a landmark is a compact information which uniquely couples a state, for problems with hidden states. Landmarks are shown to support finding good memoryless policies for Partially Observable Markov Decision Processes (POMDP) which contain at least one landmark. SarsaLandmark, as an adaptation of Sarsa(λ), is known to promise a better learning performance with the assumption that all landmarks of the problem are known in advance.

In this paper, we propose a framework built upon SarsaLandmark, which is able to automatically identify landmarks within the problem during learning without sacrificing quality, and requiring no prior information about the problem structure. For this purpose, the framework fuses SarsaLandmark with a well-known multiple-instance learning algorithm, namely Diverse Density (DD). By further experimentation, we also provide a deeper insight into our concept filtering heuristic to accelerate DD, abbreviated as DDCF (Diverse Density with Concept Filtering), which proves itself to be suitable for POMDPs with landmarks. DDCF outperforms its antecedent in terms of computation speed and solution quality without loss of generality.

The methods are empirically shown to be effective via extensive experimentation on a number of known and newly introduced problems with hidden state, and the results are discussed.

Blockchain technology has rapidly emerged as a decentralized trusted network to replace the traditional centralized intermediator. Especially, the smart contracts that are based on blockchain allow users to define the agreed behaviour among them, the execution of which will be enforced by the smart contracts. Based on this, we propose a decentralized booking system that uses the blockchain as the intermediator between hoteliers and travellers. The system enjoys the trustworthiness of blockchain, improves efficiency and reduces the cost of the traditional booking agencies. The design of the system has been formally modelled using the CSP# language and verified using the model checker Process Analysis Toolkit. We have implemented a prototype decentralized booking system based on the Ethereum ecosystem.

This paper presents a review of pattern matching techniques. The application areas for pattern matching are extensive, ranging from CAD systems to chemical analysis and from manufacturing to image processing. Published techniques and methods are classified and assessed within the context of three key issues: pattern classes, similarity types and matching methods. It has been shown that the techniques and approaches are as diverse and varied as the applications.