181 research outputs found
Value-based MORL for stochastic environments data.zip
No full textData from the experiments reported in Deng, Vamplew, Foale & Dazeley, An Empirical Investigation of Value-Based Multi-objective Reinforcement Learning for Stochastic Environments. http://arxiv.org/abs/2401.03163</p
Scalar reward is not enough : a response to Silver, Singh, Precup and Sutton (2021)
No full textThe recent paper “Reward is Enough” by Silver, Singh, Precup and Sutton posits that the concept of reward maximisation is sufficient to underpin all intelligence, both natural and artificial, and provides a suitable basis for the creation of artificial general intelligence. We contest the underlying assumption of Silver et al. that such reward can be scalar-valued. In this paper we explain why scalar rewards are insufficient to account for some aspects of both biological and computational intelligence, and argue in favour of explicitly multi-objective models of reward maximisation. Furthermore, we contend that even if scalar reward functions can trigger intelligent behaviour in specific cases, this type of reward is insufficient for the development of human-aligned artificial general intelligence due to unacceptable risks of unsafe or unethical behaviour.Funding: Flemish Government; National Cancer Institute of the U.S. National Institutes of Health [1R01CA240452-01A1]; Research Foundation Flanders (FWO) [1242021N]; Swedish Governmental Agency for Innovation Systems [NFFP7/2017-04885]; Wallenberg Artificial Intelligence, Autonomous Systems and Software Program (WASP) - Knut and Alice Wallenberg Foundation; National University of Ireland Galway Hardiman Scholarship; FAPERGS [19/2551-0001277-2]; FAPESP [2020/05165-1]</p
Recognition of Sign Language Gestures Using Neural Networks
No full text: This paper describes the structure and performance of the SLARTI (sign language recognition) system developed at the University of Tasmania. SLARTI uses a modular architecture consisting of multiple feature-recognition neural networks and a nearest-neighbour classifier to recognise Australian sign language (Auslan) hand gestures. Keywords: Sign language, hand gestures, communication aid 1 Introduction The aim of this research is to develop a prototype system for the recognition of the hand gestures used in Australian Sign Language (Auslan). The motivation behind this work is the possibility of reducing the communications barrier which exists between the deaf and hearing communities. The problems that deaf people encounter in trying to communicate with the general community are well documented (see for example [6]). In many ways the Deaf community is similar to an ethnic community in that they form a subgroup within society, complete with its own culture and language (in this case s..
More effective web search using bigrams and trigrams
No full textThis paper investigates the effectiveness of quoted bigrams and trigrams as query terms to target web search. Prior research in this area has largely focused on static corpora each containing only a few million documents, and has reported mixed (usually negative) results. We investigate the bigram/trigram extraction problem and present an extraction algorithm that shows promising results when applied to real-time web search. We also present a prototype augmented search software package that can leverage the results provided by a web search engine to assist the web searcher identify important phrases and related documents quickly. This software has received favourable feedback in a recent user survey. Copyright © 2006, David Johnson, Vishv Malhotra, & Peter Vamplew.C
Using psycholinguistic features for profiling first language of authors
No full textThis study empirically evaluates the effectiveness of different feature types for the classification of the first language of an author. In particular, it examines the utility of psycholinguistic features, extracted by the Linguistic Inquiry and Word Count (LIWC) tool, that have not previously been applied to the task of author profiling. As LIWC is a tool that has been developed in the psycholinguistic field rather than the computational linguistics field, it was hypothesized that it would be effective, both as a single type feature set because of its psycholinguistic basis, and in combination with other feature sets, because it should be sufficiently different to add insight rather than redundancy. It was found that LIWC features were competitive with previously used feature types in identifying the first language of an author, and that combined feature sets including LIWC features consistently showed better accuracy rates and average F measures than were achieved by the same feature sets without the LIWC features. As a secondary issue, this study also examined how effectively first language classification scaled up to a larger number of possible languages. It was found that the classification scheme scaled up effectively to the entire 16 language collection from the International Corpus of Learner English, when compared with results achieved on just 5 languages in previous research. 2012 ASIS&T
Participant observation of griefing in a journey through the World of Warcraft
No full textThrough the ethnographic method of participant observation in World of Warcraft, this paper aims to document various actions that may be considered griefing among the Massively Multiplayer Online Role-Playing Game community. Griefing as a term can be very subjective, so witnessing the anti-social and intentional actions first-hand can be used as a means to understand this subjectivity among players as well as produce a thorough recount of some of the toxic behavior in this genre. The participant observation was conducted across several years and expansions of World of Warcraft and the author became familiar with many griefing related actions; although some of these were perceived as acceptable game-play elements
Position : intent-aligned ai systems must optimize for agency preservation
No full textA central approach to AI-safety research has been to generate aligned AI systems: i.e. systems that do not deceive users and yield actions or recommendations that humans might judge as consistent with their intentions and goals. Here we argue that truthful AIs aligned solely to human intent are insufficient and that preservation of long-term agency of humans may be a more robust standard that may need to be separated and explicitly optimized for. We discuss the science of intent and control and how human intent can be manipulated and we provide a formal definition of agency-preserving AI-human interactions focusing on forward-looking explicit agency evaluations. Our work points to a novel pathway for human harm in AI-human interactions and proposes solutions to this challenge. Copyright 2024 by the author(s
Assessing the impact of griefing in MMORPGs using self-determination theory
No full textToxic behavior has been impacting players in online multiplayer environments since their inception. Griefing is a type of toxic behavior that focuses on player-to-player in-game disruption and is quite prevalent. However, research into the extent of the impact is still scarce. The present study investigated the impact on the psychological needs of autonomy, competence, and relatedness, as defined by the self-determination theory, for players that perform griefing (the griefers) and those subjected to griefing (the griefed). A sample of 656 respondents from massively multiplayer online role-playing game communities participated in the study. The results discovered that for the majority of players there is no change to their wellbeing, but that when there was a change, the griefed players in general were impacted more negatively, and the perpetrators were impacted more positively. Significant associations also revealed that the magnitude of impacts increased as the player was subjected to or performed griefing more frequently. © 2024 The Author
Explainable robotic systems: understanding goal-driven actions in a reinforcement learning scenario
No full textRobotic systems are more present in our society everyday. In human–robot environments, it is crucial that end-users may correctly understand their robotic team-partners, in order to collaboratively complete a task. To increase action understanding, users demand more explainability about the decisions by the robot in particular situations. Recently, explainable robotic systems have emerged as an alternative focused not only on completing a task satisfactorily, but also on justifying, in a human-like manner, the reasons that lead to making a decision. In reinforcement learning scenarios, a great effort has been focused on providing explanations using data-driven approaches, particularly from the visual input modality in deep learning-based systems. In this work, we focus rather on the decision-making process of reinforcement learning agents performing a task in a robotic scenario. Experimental results are obtained using 3 different set-ups, namely, a deterministic navigation task, a stochastic navigation task, and a continuous visual-based sorting object task. As a way to explain the goal-driven robot’s actions, we use the probability of success computed by three different proposed approaches: memory-based, learning-based, and introspection-based. The difference between these approaches is the amount of memory required to compute or estimate the probability of success as well as the kind of reinforcement learning representation where they could be used. In this regard, we use the memory-based approach as a baseline since it is obtained directly from the agent’s observations. When comparing the learning-based and the introspection-based approaches to this baseline, both are found to be suitable alternatives to compute the probability of success, obtaining high levels of similarity when compared using both the Pearson’s correlation and the mean squared error. © 2021, The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature
An empirical comparison of two common multiobjective reinforcement learning algorithms
No full textIn this paper we provide empirical data of the performance of the two most commonly used multiobjective reinforcement learning algorithms against a set of benchmarks. First, we describe a methodology that was used in this paper. Then, we carefully describe the details and properties of the proposed problems and how those properties influence the behavior of tested algorithms. We also introduce a testing framework that will significantly improve future empirical comparisons of multiobjective reinforcement learning algorithms. We hope this testing environment eventually becomes a central repository of test problems and algorithms The empirical results clearly identify features of the test problems which impact on the performance of each algorithm, demonstrating the utility of empirical testing of algorithms on problems with known characteristics. © 2012 Springer-Verlag
- …
