Filters








15,586 Hits in 4.2 sec

Concept Learning Games: The Game of Query and Response

Nima Mirbakhsh, Arman Didandeh, Mohsen Afsharchi
2010 2010 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology  
This article deals with the issue of concept learning and tries to have a game theoretic view over the process of cooperative concept learning among agents in a multi-agent system, in which an extreme  ...  We study the cooperative view and give a novel idea to use in competitive environments based on the solution concepts of game theory and an innovative idea of concept scores over an ontology, which is  ...  The general idea of concept learning games is studied in the big context of concept learning, in which the "concept learning and reformation" is explored both from an objectbased and also feature-based  ... 
doi:10.1109/wi-iat.2010.161 dblp:conf/iat/MirbakhshDA10 fatcat:odjruamhs5bq3nqqr47jn7zpri

Simulating processes of concept formation and communication

Timo Honkela, Ville Könönen, Tiina Lindh‐Knuutila, Mari‐Sanna Paukkeri
2008 Journal of Economic Methodology  
We consider, in particular, the role of unsupervised learning in the formation of agents' conceptual models, the relative subjectivity of these models, and the communication and learning processes that  ...  lead into intersubjective sharing of concepts.  ...  Jesús Zamora Bonilla who kindly invited us to give a presentation in the Economics and Language workshop in Madrid in June 2006. This article is an extension of the paper presented in the workshop.  ... 
doi:10.1080/13501780802321350 fatcat:2tb2k3ghbjd2llvwzzc7hw37pm

Transfer Learning Method Using Ontology for Heterogeneous Multi-agent Reinforcement Learning

Hitoshi Kono, Akiya Kamimura, Kohji Tomita, Yuta Murata, Tsuyoshi Suzuki
2014 International Journal of Advanced Computer Science and Applications  
A multiagent robot system (MARS) that utilizes reinforcement learning and a transfer learning method has recently been studied in realworld situations.  ...  In prior research, we developed ontology-based inter-task mapping as a core technology for hierarchical transfer learning (HTL) method and investigated its effectiveness in a dynamic multi-agent environment  ...  Transfer Learning in a Multi-agent Domain In recent years, transfer learning has been investigated not only for single-agent systems but also for MARSs.  ... 
doi:10.14569/ijacsa.2014.051022 fatcat:iavbukidujayzp3q33izppabr4

Interactive Ontology-Based User Knowledge Acquisition: A Case Study [chapter]

Lora Aroyo, Ronald Denaux, Vania Dimitrova, Michael Pye
2006 Lecture Notes in Computer Science  
We show the deployment of the agent in a use case for personalized management of learning content, which has been evaluated in three studies with users.  ...  This paper presents an approach to eliciting a user's conceptualization by engaging in an ontology-driven dialog. This is implemented as an OWL-based domainindependent diagnostic agent.  ...  The research was partly supported by the UK-Netherlands Partnership in Science program and the EU Network of Excellence PROLEARN.  ... 
doi:10.1007/11762256_41 fatcat:bi2vktor45gprohyjutgxk4n4u

Playing a Strategy Game with Knowledge-Based Reinforcement Learning

Viktor Voss, Liudmyla Nechepurenko, Rudi Schaefer, Steffen Bauer
2020 SN Computer Science  
The results show that the KB-RL system is able to play and complete the full FreeCiv game, and to win against the computer players in various game settings.  ...  We use the strategy game CIVILIZATION to showcase the capabilities of our KB-RL method. Particularly, the open-source version of the game FreeCiv was played by KB-RL agents.  ...  More recently, conflict resolution has been intensively studied in multi-agent systems (MAS).  ... 
doi:10.1007/s42979-020-0087-8 fatcat:yl4n5gnkuzhq5e775y7f44jifm

Pow-Wow: A Dataset and Study on Collaborative Communication in Pommerman [article]

Takuma Yoneda, Matthew R. Walter, Jason Naradowsky
2020 arXiv   pre-print
In multi-agent learning, agents must coordinate with each other in order to succeed. For humans, this coordination is typically accomplished through the use of language.  ...  In this work we perform a controlled study of human language use in a competitive team-based game, and search for useful lessons for structuring communication protocol between autonomous agents.  ...  Acknowledgements We would like to express our deep gratitude to the folks in TTIC and University of Chicago who participated in the study, and the brilliant people in Preferred Networks and colleagues  ... 
arXiv:2009.05940v1 fatcat:wwkwmeea3rh5bm6ilg7ln3ecai

Automated ontology evolution in a multi-agent system

Mohsen Afsharchi, Behrouz H. Far
2006 Proceedings of the 1st international conference on Scalable information systems - InfoScale '06  
In this paper multi-agent supervised learning of concepts among individual agents with diverse conceptualization and different ontologies is introduced and demonstrated through an intuitive example in  ...  This research addresses the formation of new concepts and their corresponding ontology in a multiagent system where individual autonomous agents try to learn new concepts by consulting several other agents  ...  Ontology ( i O ) We believe that concept learning in a multi-agent system does not make sense when agents use a common shared ontology because in this case concept learning simply can be done by copying  ... 
doi:10.1145/1146847.1146863 dblp:conf/infoscale/AfsharchiF06 fatcat:32edpfij75drjpgdh75ddvpxvq

MOLPP, a New Generic Approach to Design a System for Monitoring Player Progress in Serious Games

Yassine El, Mohamed Khaldi
2018 International Journal of Computer Applications  
Thus, we propose a monitoring system called MOLPP (Monitoring Learner -Player Progress in Serious Games) which adopts a new generic approach based mainly on Anderson's ACT-R theory.  ...  The growing interest in the use of Serious Games in education raises many researches questions and involves some concerns, particularly the ability to track and understand the path of a learner -player  ...  process in the production unit  Domain ontology Fig 7 : 7 Multi-Agent Architecture of the MOLPP System  ... 
doi:10.5120/ijca2018916495 fatcat:v2um6lq6qrdh7k35ic64bnza4u

Ontology Based Business Simulations

Thomas Farrenkopf, Michael Guckert, Neil Urquhart, Simon Wells
2016 Journal of Artificial Societies and Social Simulation  
We demonstrate how ontologies can be integrated into the BDI concept utilising the Jadex agent framework.  ...  We use a framework, developed previously, known as AGADE within which each agent evolves its knowledge using an ontology maintained during the simulation.  ...  Simulation of real world scenarios in business games is an important application of complex adaptive social systems.  ... 
doi:10.18564/jasss.3266 fatcat:wap4awgwojedrfi3t7e73zr5oq

Approaches for semantic interoperability between domain ontologies

Bhavna Orgun, Mark Dras, Abhaya Nayak, Geoff James
2008 Expert systems  
Domain ontologies and knowledge-based systems have become very important in the agent and semantic web communities.  ...  In this paper we survey the approaches that have been proposed for providing interoperability among domain ontologies.  ...  With the growing trend in ontology based multi-agent systems this need has become imperative.  ... 
doi:10.1111/j.1468-0394.2008.00461.x fatcat:5oh6w4s7jvcnbjsteo3anokwri

A Knowledge Engineering Approach to Computational Creativity in Sound Design

Eugene Cherny, Johan Lilius, Johannes Brusila, Dmitry Mouromtsev
2016 Zenodo  
This paper proposes an approach to sound design based on knowledge engineering.  ...  The multi-agent system concept lacks specification on agents communication and how the system should be embedded in the process of the actual sound designer.  ...  Multi-agent System for Sound Generation As discussed in the previous section, the sound design process starts with a concept requirement-an informal description of the sound to be created.  ... 
doi:10.5281/zenodo.4289300 fatcat:ktt7behcdfdd7jsfvhvl44exfi

Computational Creativity Conceptualisation Grounded on ICCC Papers

Senja Pollak, Biljana Mileva-Boshkoska, Dragana Miljkovic, Geraint A. Wiggins, Nada Lavrac
2016 International Conference on Computational Creativity  
In information science, it is considered that domain conceptualization can be realized by (one or several) ontologies.  ...  This approach affords an interesting opportunity for automated historiography of a research field.  ...  poems, words, poetry, artefacts, story, evaluating, creativity system, predict, text, creativity Games games, blending, design, analogy, player, conceptual, games design, angelina, ontology, agents Conceptual  ... 
dblp:conf/icccrea/PollakMMWL16 fatcat:kd3zbeeqv5e4zcdpu7l6uminjq

Mutual online concept learning for multiple agents

Jun Wang, Les Gasser
2002 Proceedings of the first international joint conference on Autonomous agents and multiagent systems part 1 - AAMAS '02  
To create multi-agent systems that are both adaptive and open, agents must collectively learn to generate and adapt their own concepts, ontologies, interpretations, and even languages actively in an online  ...  This paper presents a framework for mutual online concept learning (MOCL) in a shared world. MOCL extends classical online concept learning from single-agent to multi-agent settings.  ...  ACKNOWLEDGMENTS This work was partially supported under NSF grant 9981-797, and by the Information Systems Research Lab (ISRL) of the Graduate School of Library and Information Science.  ... 
doi:10.1145/544829.544830 fatcat:2pdmbzc4pfhe3lphxfpfzkrmta

Mutual online concept learning for multiple agents

Jun Wang, Les Gasser
2002 Proceedings of the first international joint conference on Autonomous agents and multiagent systems part 1 - AAMAS '02  
To create multi-agent systems that are both adaptive and open, agents must collectively learn to generate and adapt their own concepts, ontologies, interpretations, and even languages actively in an online  ...  This paper presents a framework for mutual online concept learning (MOCL) in a shared world. MOCL extends classical online concept learning from single-agent to multi-agent settings.  ...  ACKNOWLEDGMENTS This work was partially supported under NSF grant 9981-797, and by the Information Systems Research Lab (ISRL) of the Graduate School of Library and Information Science.  ... 
doi:10.1145/544741.544830 dblp:conf/atal/WangG02 fatcat:4v6dcy6ks5c35jqys7v3zto4j4

An Experience on Reputation Models Interoperability Based on a Functional Ontology

Laurent Vercouter, Sara J. Casare, Jaime Simão Sichman, Anarosa Brandão
2007 International Joint Conference on Artificial Intelligence  
In this paper we consider the case of reputation models by describing an experience of using several existing technologies to allow agents to interoperate when they use reputation notions/values during  ...  Interaction between heterogeneous agents can raise some problems since agents may not use the same models and concepts.  ...  Acknowledgements This work has been developed in the project "Integration of the Functional Ontology of Reputation into the Agent Reputation Testbed (ART)" supported by FAPESP, Brazil, grant number 2005  ... 
dblp:conf/ijcai/VercouterCSB07 fatcat:3lysiphdnjd7ddltkqbmbtiwna
« Previous Showing results 1 — 15 out of 15,586 results