E. Daman Bsc, E. Daman Bsc · 2016
Copyright c © 2008 T his thesis investigates how methods for collaborative agents can be applied to the AIBO (Artificial Intelligence roBOt) of SONY Corporation. A method for collaboration will be explained in detail, and the design and implementation of a working prototype will be presented. The software works in an ad-hoc wifi network with clients that can connect and disconnect at all times. Data can be shared between the clients (AIBOs) so that they can
Cited by 0
Weimao Ke, Javed Mostafa, Yueyu Fu · 2007
We developed a multi-agent framework where agents had limited/distributed knowledge for document classification and collaborated with each other to overcome the knowledge distribution. Each agent was equipped with a certain learning algorithm for predicting potential collaborators, or helping agents. We conducted experimental research on a standard news corpus to examine the impact of two learning algorithms: Pursuit Learning and Nearest Centroid Learning. For a fundamental retrieval operation, namely classification, both algorithms achieved competitive classification effectiveness and efficiency. Subsequently, the impact of the learning exploration rate and the maximum collaboration range on classification effectiveness and efficiency were examined. Close investigation of agent learning dynamics revealed increasing and stabilizing patterns that were enhanced by the learning algorithms.
Cited by 9
Shirley Yingxin Wu, Jure Leskovec, James Zou et al. · Stanford Digital Repository · 2026
Cited by 0Open access
Bonnie Nardi, James R. Miller, David J. Wright · Communications of the ACM · 1998
article Free Access Share on Collaborative, programmable intelligent agents Authors: Bonnie A. Nardi AT&T Labs Research, Menlo Park, Calif. AT&T Labs Research, Menlo Park, Calif.View Profile , James R. Miller Apple's Advanced Technology Apple's Advanced TechnologyView Profile , David J. Wright Apple's Operating Systems Technologies Apple's Operating Systems TechnologiesView Profile Authors Info & Claims Communications of the ACMVolume 41Issue 3March 1998 pp 96–104https://doi.org/10.1145/272287.272331Online:01 March 1998Publication History 86citation1,307DownloadsMetricsTotal Citations86Total Downloads1,307Last 12 Months28Last 6 weeks9 Get Citation AlertsNew Citation Alert added!This alert has been successfully added and will be sent to:You will be notified whenever a record that you have chosen has been cited.To manage your alert preferences, click on the button below.Manage my Alerts New Citation Alert!Please log in to your account Save to BinderSave to BinderCreate a New BinderNameCancelCreateExport CitationPublisher SiteeReaderPDF
Cited by 173Open access
Chadwick Carreto Arellano, Gabriela De Jesus Lopez Ruiz, Rodolfo Romero Herrera · 2015
Currently a predominant need for organizations is the support service that can provide its customers and partners, this assistance is an issue of great importance for the value involving customers and pays off in image for the organization. Thus the investment to sustain this service you get to become significant figures that could be saved by implementing Agents Assistance (AA) based software, which are always available to customers in most cases solve the most common problems users. The significantly lower investment for companies and an image is projected technological domain. It is for this reason that in this paper an architecture for implementing agents Assistance is defined, it explains an overview of the architecture design and implementation in different environments looking that can be integrated in collaborative environments which allow increasing knowledge and ability to service agents.
Cited by 0
2009
Abstract This paper describes eXAT, an experimental agent pro-gramming platform, based on the Erlang language, designed by the authors. The platform provides an "all-in-one " framework for the design, with a single tool, of agent intelligence, agent behaviour and agent communica-tion. This is made possible in eXAT by means of the integration of an Erlang-based expert system engine, togetherwith an execution environment for agent behaviours based on object-oriented finite-state machines. Such a system al-lows transition triggering on the basis of agent's mental state. Similarly, the provided agent communication facil-ity, which is based on the exchange of ACL speech acts, can not only trigger behaviours but also influence agent's men-tal state according to FIPA-ACL semantics. 1.
Cited by 0
2007
Abstract. This paper deals with identifying roles for coordination agents in a future collaborative telelearning environment. The current practice of students participating in a netbased simulation marketing game on-campus, is studied with an eye on designing a future collaborative telelearning environment where this same net-based simulation game will be central. The work described in this paper is situated within the theoretical foundations of computer supported collaborative learning (CSCL). In particular Salomon’s writings on genuine interdependence in CSCL, and work on coordination from a computer supported cooperative work (CSCW) perspective provide the view on collaborative telelearning. Viewing collaborative telelearning from a coordination theory perspective offers a means of understanding the inter-relationships between actors and entities and how these relationships can and should be supported. In this paper an extended definition of coordination is given and a set of actor (inter)dependencies and related coordination processes for collaborative telelearning is proposed. Then, coordination agents are suggested as a means of managing and supporting the identified (inter)dependencies and examples of possible coordination agent roles are given.
Cited by 0
N.G. Röling, Janice Jiggins · Biological Diversity · 2001
Cited by 5
Charles Desjardins, Julien Laumônier, Brahim Chaib-draa · IGI Global eBooks · 2011
This chapter studies the use of agent technology in the domain of vehicle control. More specifically, it illustrates how agents can address the problem of collaborative driving. First, the authors briefly survey the related work in the field of intelligent vehicle control and inter-vehicle cooperation that is part of Intelligent Transportation Systems (ITS) research. Next, they detail how these technologies are especially adapted to the integration, for decision-making, of autonomous agents. In particular, they describe an agent-based cooperative architecture that aims at controlling and coordinating vehicles. In this context, the authors show how reinforcement learning can be used for the design of collaborative driving agents, and they explain why this learning approach is well-suited for the resolution of this problem.Request access from your librarian to read this chapter's full text.
Cited by 0
David G. Sullivan, Barbara J. Grosz, Sarit Kraus · Digital Access to Scholarship at Harvard (DASH) (Harvard University) · 2002
Research on resource-bounded agents has established that rational agents need to be able to revise their commitments in the light of new opportunities. In the context of collaborative activities, rational agents must be able to reconcile their intentions to do team-related actions with other conflicting intentions. The SPIRE experimental system allows the process of intention reconciliation in team contexts to be simulated and studied. Prior work with SPIRE examined the effect of team norms, environmental factors, and agent utility functions on individual and group outcomes for homogeneous groups of agents. This paper extends these results to situations involving heterogeneous groups in which agents use different utility functions. The paper provides new illustrations of the ways in which SPIRE can reveal unpredicted interactions among the variables involved, and it suggests preliminary principles for designers of collaborative agents.
Cited by 42Open access
Michael S. Miller, Jianwen Yin, Richard A. Volz et al. · 2000
Cited by 0
Federico Bergenti, Mercedes Ruiz Garijo, Agostino Poggi et al. · 2002
This paper presents a software framework, called Collaborator, to provide a shared workspace supporting the activities of virtual teams. This system exploits seamless integration of standard Web technologies with agent technologies, enhancing the classic Web communication mechanisms to support synchronous sharing of applications, and its use through emerging technologies such as: third generation of mobile networks and terminals, and new generation of home appliances. The system is enhanced by two types of agents: personal agents and session management agents. Personal agents, one for each user, are in charge of adapting the work environment to the user's preferences and habits. Session management agents, one for each collaborative session, are responsible for the management of the communication with the personal agents of the users involved in a virtual meeting.
Cited by 2
Shang, Xiumin · eScholarship (California Digital Library) · 2023
Autonomous virtual agents have been employed in different areas, spanning applications from education and training to gaming and e-commerce. In particular, agents of human-like appearance, or virtual human agents, have been greatly improved over the years with the advancement of technologies in machine learning, natural language processing and computer graphics. This dissertation addresses topics related to the design and training of virtual human agents for collaborative tasks.On the design front, this thesis presents user studies investigating the effect of agent gender and feedback strategies on instructional object manipulation tasks. The obtained findings show that, although agent gender has no significant effect on user preference or performance, users find female agents to be more attractive. Comparing suggestive feedback and correctness feedback strategies, it is found that correctness feedback is preferred by the users and leads to a 65% shorter task completion time.On the training front, the focus is on collaborative tasks controlled by Deep Reinforcement Learning (DRL). Three important challenges are addressed: sequential multi-phase tasks, collaborative learning of motor tasks in a physics-based environment, and addressing realism and robustness. First, to train agents for collaborative multi-phase tasks the Constrained Multi-agent Soft Actor Critic (C-MSAC) approach is proposed. It is shown that this approach achieves better mean episode reward, generalizability and robustness to disturbance when compared with an unconstrained multi-agent learning baseline. Second, the original inverse kinematics approach is replaced with physics-based control which leads to more natural movements and improves robustness against variations to physical parameters of the environment.Finally, the Constrained Robust Soft Actor Critic (C-RSAC) approach is proposed to train a single robust agent using the policies obtained from C-MSAC for initialization. C-RSAC uses noise augmentation in the action space of one of the agents to improve robustness of the collaborating agent. It is shown that C-RSAC leads to an improved mean episode reward compared to C-MSAC when collaborating with a noisy agent.In summary, this thesis investigates several important aspects related to autonomous collaborative virtual human agents such as gender, appearance, feedback strategies, collaborative training, physics-based animation and robustness. The proposed C-MSAC approach for multi-phase multi-agent training and C-RSAC approach for multi-phase single agent robust training represent new contributions to the emerging area of autonomous virtual trainers. Overall the contributions from this thesis inform the design and modeling of collaborative virtual human agents, furthering the goal of enabling these agents to assist humans on various applications of virtual trainers.
Cited by 0Open access
CentAUR (University of Reading) · 2007
Would a research assistant - who can search for ideas related to those you are working on, network with others (but only share the things you have chosen to share), doesn’t need coffee and who might even, one day, appear to be conscious - help you get your work done? Would it help your students learn? \n \nThere is a body of work showing that digital learning assistants can be a benefit to learners. It has been suggested that adaptive, caring, agents are more beneficial. Would a conscious agent be more caring, more adaptive, and better able to deal with changes in its learning partner’s life? \n \nAllow the system to try to dynamically model the user, so that it can make predictions about what is needed next, and how effective a particular intervention will be. Now, given that the system is essentially doing the same things as the user, why don’t we design the system so that it can try to model itself in the same way? This should mimic a primitive self-awareness. \n \nPeople develop their personalities, their identities, through interacting with others. It takes years for a human to develop a full sense of self. Nobody should expect a prototypical conscious computer system to be able to develop any faster than that. How can we provide a computer system with enough social contact to enable it to learn about itself and others? \n \nWe can make it part of a network. Not just chatting with other computers about computer ‘stuff’, but involved in real human activity. Exposed to ‘raw meaning’ – the developing folksonomies coming out of the learning activities of humans, whether they are traditional students or lifelong learners (a term which should encompass everyone). \n \nHumans have complex psyches, comprised of multiple strands of identity which reflect as different roles in the communities of which they are part – so why not design our system the same way? With multiple internal modes of operation, each capable of being reflected onto the outside world in the form of roles – as a mentor, a research assistant, maybe even as a friend. \n \nBut in order to be able to work with a human for long enough to be able to have a chance of developing the sort of rich behaviours we associate with people, the system needs to be able to function in a practical and helpful role. Unfortunately, it is unlikely to get a free ride from many people (other than its developer!) – so it needs to be able to perform a useful role, and do so securely, respecting the privacy of its partner. \n \nCan we create a system which learns to be more human whilst helping people learn?
Cited by 0
Rui Prada, Ana Paiva · Lecture notes in computer science · 2005
Cited by 9
The International Foundation for Autonomous Agents and Multiagent Systems 2021, Carroll, Micah, Ciosek, Kamil et al. · Underline Science Inc. · 2021
Artificial agents trained by deep reinforcement learning will likely encounter novel situations after deployment that were never seen during training. Our agent must be to handle such situations well. However, if we cannot rely on the average training or validation reward as a metric, then how can we effectively evaluate robustness? We take inspiration from the practice of in software engineering. Specifically, we suggest that when designing AI agents that collaborate with humans, designers should search for potential edge cases in and and write tests which check that the behavior of the agent in these edge cases is reasonable. We apply this methodology to build a suite of unit tests for the Overcooked-AI environment, and use this test suite to evaluate three proposals for improving robustness. We find that the test suite provides significant insight into the effects of these proposals that were generally not revealed by looking solely at the average validation reward. For our full paper, see https://arxiv.org/abs/2101.05507 arxiv.org/abs/2101.05507
Cited by 0Open access
Yinfeng Yu, Changan Chen, Lele Cao et al. · 2023
As humans, we hear sound every second of our life. The sound we hear is often affected by the acoustics of the environment surrounding us. For example, a spacious hall leads to more reverberation. Room Impulse Responses (RIR) are commonly used to characterize environment acoustics as a function of the scene geometry, materials, and source/receiver locations. Traditionally, RIRs are measured by setting up a loudspeaker and microphone in the environment for all source/receiver locations, which is time-consuming and inefficient. We propose to let two robots measure the environment's acoustics by actively moving and emitting/receiving sweep signals. We also devise a collaborative multi-agent policy where these two robots are trained to explore the environment's acoustics while being rewarded for wide exploration and accurate prediction. We show that the robots learn to collaborate and move to explore environment acoustics while minimizing the prediction error. To the best of our knowledge, we present the very first problem formulation and solution to the task of collaborative environment acoustics measurements with multiple agents.
Cited by 8Open access
P. A. Knott, Micah Carroll, Sam Devlin et al. · Repository@Nottingham (University of Nottingham) · 2021
Artificial agents trained by deep reinforcement learning will likely encounter novel situations after deployment that were never seen during training. Our agent must be robust to handle such situations well. However, if we cannot rely on the average training or validation reward as a metric, then how can we effectively evaluate robustness? We take inspiration from the practice of unit testing in software engineering. Specifically, we suggest that when designing AI agents that collaborate with humans, designers should search for potential edge cases in possible partner behavior and possible states encountered, and write tests which check that the behavior of the agent in these edge cases is reasonable. We apply this methodology to build a suite of unit tests for the Overcooked-AI environment, and use this test suite to evaluate three proposals for improving robustness. We find that the test suite provides significant insight into the effects of these proposals that were generally not revealed by looking solely at the average validation reward. For our full paper, see https://arxiv.org/abs/2101.05507 arxiv.org/abs/2101.05507
Cited by 0Open access
Sourish Chaudhuri, Rohit Kumar, Iris Howley et al. · Frontiers in artificial intelligence and applications · 2009
We present the results of a study in which we contrast alternative forms of collaborative learning support in the midst of a collaborative design task in which students negotiate between increasing power and increasing environmental friendliness. Our research question is whether interactive instructional support in collaborative learning environments is more effective when it is offered as solicited or unsolicited help. The finding from our classroom study is that dialogue-based support is more effective in this collaborative context when invitations for help in the form of pointer hints are offered automatically, but dialogue agents are only provided when the invitation is explicitly accepted.
Cited by 43
James Allen, Lucian Galescu, Choh Man Teng et al. · AI Magazine · 2020
Dialogue is a very active area of research currently, both in developing new computational techniques for robust dialogue systems and in the active fielding of commercial conversational assistants such as Apple's Siri and Amazon's Alexa. This article argues that, while current techniques can be used to design effective dialogue‐based systems for very simple tasks, they are unlikely to generalize to conversational interfaces that enhance human ability to solve complex tasks by interacting with artificial intelligence reasoning and modeling systems. We explore some of the challenges of tackling such complex tasks and describe a dialogue model designed to meet these challenges. We illustrate our approach with examples of several implemented systems that use this framework.
Cited by 7Open access