Filters








30,320 Hits in 2.8 sec

Validating a Novel Conflict Resolution Strategy Selection Method (ConfRSSM) Via Multi-Agent Simulation

Alicia Y.C., Ghusoon Salim
2017 International Journal of Advanced Computer Science and Applications  
Selecting a suitable conflict resolution strategy when conflicts appear in multi-agent environments is a hard problem.  ...  strengths and confidence levels of the conflicting agents.  ...  resolution in multi agent systems [24] . e) To validate (d) using agent-based simulation.  ... 
doi:10.14569/ijacsa.2017.080824 fatcat:uiruya4wlra6zigq2uptcxbgem

Abmarl: Connecting Agent-Based Simulations with Multi-Agent Reinforcement Learning

Edward Rusu, Ruben Glatt
2021 Journal of Open Source Software  
Abmarl is a package for developing Agent-Based Simulations and training them with Multi-Agent Reinforcement Learning (MARL).  ...  We define an Agent-Based Simulation Interface and Simulation Manager, which control which agents interact with the simulation at each step.  ...  Multi-Agent Reinforcement Learning (MARL).  ... 
doi:10.21105/joss.03424 fatcat:irxecsdxjncyzf2watdatjq5qi

Educational Resources Recommendation System for a heterogeneous Student Group

Paula Andrea RODRÍGUEZ MARÍN, Mauricio GIRALDO, Valentina TABARES, Néstor DUQUE, Demetrio OVALLE
2016 Advances in Distributed Computing and Artificial Intelligence Journal  
In this sense, multi-agent system (MAS) can be used to simulate the features of the students in the group, including their learning style, in order to help the professor find the best resources for your  ...  Advances in Distributed Computing and Artificial Intelligence Journal ©Ediciones Universidad de Salamanca / cc by-nc-nd 21 KEYWORD ABSTRACT Educational resources; Metadata; Multi-agent systems; Recommendation  ...  agent is the basis for creating the simulation of each student.  ... 
doi:10.14201/adcaij2016532130 fatcat:rljkhx6ng5dejchn2qeselg5ci

Microscopic Traffic Simulation by Cooperative Multi-agent Deep Reinforcement Learning [article]

Giulio Bacchiani, Daniele Molinari, Marco Patander
2019 arXiv   pre-print
In particular, the algorithm called Asynchronous Advantage Actor-Critic has been extended to a multi-agent scenario in which every agent needs to learn to interact with other similar agents.  ...  In this paper, this problem is addressed by developing a microscopic simulator using a Deep Reinforcement Learning Algorithm based on a combination of visual frames, representing the perception around  ...  Agents are collectively trained in a multi-agent fashion so that cooperative behaviors can emerge, gradually inducing agents to learn to interact with each other.  ... 
arXiv:1903.01365v1 fatcat:ldklue4w7vfuxcm2grazbwuw74

A Teaching System for Hands-on Quadcopter Control

Paul N. Beuchat, Yvonne R. Stürz, John Lygeros
2019 IFAC-PapersOnLine  
Section 2 describes the multi-agent software system we developed to enable a distributed, flexible, and easyto-manage environment for teaching quadcopter control.  ...  Section 2 describes the multi-agent software system we developed to enable a distributed, flexible, and easyto-manage environment for teaching quadcopter control.  ... 
doi:10.1016/j.ifacol.2019.08.120 fatcat:bsclj32ycbhkdfwnx7hsfksziu

Hallucinating Value: A Pitfall of Dyna-style Planning with Imperfect Environment Models [article]

Taher Jafferjee, Ehsan Imani, Erin Talvitie, Martha White, Micheal Bowling
2020 arXiv   pre-print
Dyna-style reinforcement learning (RL) agents improve sample efficiency over model-free RL agents by updating the value function with simulated experience generated by an environment model.  ...  However, it is often difficult to learn accurate models of environment dynamics, and even small errors may result in failure of Dyna agents.  ...  In contrast, Uniterated One-step Predecessor and Multi-step Predecessor never update toward a simulated state. Their learning curves show superior performance to Q-learning.  ... 
arXiv:2006.04363v1 fatcat:ldzykfdgpran7bqtt2io4oyraa

A context-aware adaptive learning system using agents

Mahkameh Yaghmaie, Ardeshir Bahreininejad
2011 Expert systems with applications  
The proposed architecture is based upon multi-agent systems and uses both Sharable Content Object Reference Model (SCORM) 2004 and semantic Web ontology for learning content storage, sequencing and adaptation  ...  This system has been implemented upon a well known open-source LMS and its functionalities are demonstrated through the simulation of a scenario mimicing the real life conditions.  ...  The proposed system is based on multi-agent concepts.  ... 
doi:10.1016/j.eswa.2010.08.113 fatcat:6bcscawevfc4zdufgnsbmegl2a

An Artificial Neural Network (ANN)-Based Learning Agent for Classifying Learning Styles in Self-Regulated Smart Learning Environment

Yusufu Gambo, Muhammad Zeeshan Shakir
2021 International Journal of Emerging Technologies in Learning (iJET)  
Based on these skills, this paper develops a learning agent to classify students' learning styles using artificial neural networks (ANN), which mapped to Felder-Silverman Learning Style Model (FSLSM) as  ...  Style dimensions.  ...  The authors compared the simulated experiment with Felder-Silverman and Kolb's learning styles, multi-layer perceptron, and decision tree.  ... 
doi:10.3991/ijet.v16i18.24251 fatcat:garllrx3vzdbhhbikkjhefmurq

WarpDrive: Extremely Fast End-to-End Deep Multi-Agent Reinforcement Learning on a GPU [article]

Tian Lan, Sunil Srinivasa, Huan Wang, Stephan Zheng
2021 arXiv   pre-print
Together, this allows the user to easily run thousands of concurrent multi-agent simulations and train on extremely large batches of experience.  ...  As such, WarpDrive is a fast and extensible multi-agent RL platform to significantly accelerate research and development.  ...  Use imperative and stateful code to build complex multi-agent simulation logic with interacting agents. 7.  ... 
arXiv:2108.13976v3 fatcat:c2myxz6265fevj4xq6xryszd2a

Anchoring Knowledge in Interaction: Towards a Harmonic Subsymbolic/Symbolic Framework and Architecture of Computational Cognition [chapter]

Tarek R. Besold, Kai-Uwe Kühnberger, Artur d'Avila Garcez, Alessandro Saffiotti, Martin H. Fischer, Alan Bundy
2015 Lecture Notes in Computer Science  
, e.g., multi-modal, hybrid. ...user modeling and communication through learning and adaptation. ...interaction styles: Action-centered, embodied, multi-modal. ...knowledge repositories: Different levels  ...  including other agents).  ...  Knowledge as... ...multi-layered phenomenon appearing at different levels of abstraction. ...promoting interaction between levels. ...influenced by interaction between agent and environment (potentially  ... 
doi:10.1007/978-3-319-21365-1_4 fatcat:w5vi2xkbjjanlckvfhaumssmiq

VR-Goggles for Robots: Real-to-sim Domain Adaptation for Visual Control [article]

Jingwei Zhang, Lei Tai, Peng Yun, Yufeng Xiong, Ming Liu, Joschka Boedecker, Wolfram Burgard
2019 arXiv   pre-print
In this paper, we deal with the reality gap from a novel perspective, targeting transferring Deep Reinforcement Learning (DRL) policies learned in simulated environments to the real-world domain for visual  ...  We propose this as a lightweight, flexible, and efficient solution for visual control, as 1) no extra transfer steps are required during the expensive training of DRL agents in simulation; 2) the trained  ...  or unseen features of real images back into the simulated style, which the agents have already learned how to deal with during training in the simulation.  ... 
arXiv:1802.00265v4 fatcat:xefllbypnvdqhbrequ32dydqpy

Optimising Long-Term Outcomes using Real-World Fluent Objectives: An Application to Football [article]

Ryan Beal, Georgios Chalkiadakis, Timothy J. Norman, Sarvapali D. Ramchurn
2021 arXiv   pre-print
We develop Markov chain Monte Carlo and deep learning-based algorithms that make use of the fluent objectives in order to learn from prior games and other games in the environment and increase the teams  ...  Simulations of our approach using real-world datasets from 760 matches shows that by using optimised tactics with our fluent objective and prior games, we can on average increase teams mean expected finishing  ...  We can learn a set of weights W that relate to how effective given style/formation pairs (actions that are made in the multi-step games) that we select in our games are against given oppositions style/  ... 
arXiv:2102.09469v1 fatcat:ljhmw2m6ofez7mjkduvwvbqasu

Design of an Adaptive e-Learning System based on Multi-Agent Approach and Reinforcement Learning

H. El Fazazi, M. Elgarej, M. Qbadou, K. Mansouri
2021 Engineering, Technology & Applied Science Research  
In this paper, a design of an adaptative e-learning system based on a multi-agent approach and reinforcement learning is presented.  ...  The application of the multi-agent approach in adaptive e-learning systems can enhance the learning process quality by customizing the contents to students' needs.  ...  We have tried to propose a system that takes into consideration the learning styles, knowledge level, and disabilities of the students by applying the multi-agent approach and reinforcement learning to  ... 
doi:10.48084/etasr.3905 fatcat:n4vy5awym5cy3hrkj5tk3u4yhu

Improvising in Creative Symbolic Interaction [chapter]

Gérard Assayag
2016 Lecture Notes Series, Institute for Mathematical Sciences, National University of Singapore  
while "keeping in style".  ...  Performers improvising along with Symbolic Interaction systems experiment a unique artistic situation where they interact with musical (and possibly multi-modal) agents which develop in their own ways  ...  It will be possible in this way to construct intelligent multi-agent systems well equipped for dealing credibly with more complex musical situations involving a variety of styles.  ... 
doi:10.1142/9789813140103_0004 fatcat:zz2avfpjxbapfakzpkesy54pga

Ineffective Organizational Practices at NASA: A Dynamic Network Analysis

Craig Schreiber, Kathleen M. Carley
2005 Social Science Research Network  
As such, multi-agent network models can capture the complexities of NASA structure at various levels.  ...  for the representation of individual cognitive agents who can take action, learn and alter the network -organizational adaptation.  ...  Dynamic network analysis combines multi-level, multi-mode social network analysis with cognitive science and multi-agent simulation to provide a methodology for modeling the dynamics of complex and adaptive  ... 
doi:10.2139/ssrn.2726789 fatcat:iofoiik37zgbrfmlwrx2vhjozu
« Previous Showing results 1 — 15 out of 30,320 results