Filters








3,275 Hits in 3.1 sec

An Intelligent Inference System for Robot Hand Optimal Grasp Preshaping

Cabbar Veysel Baysal, Aydan M. Erkmen
2010 International Journal of Computational Intelligence Systems  
incremental learning.  ...  This paper presents a novel Intelligent Inference System (IIS) for the determination of an optimum preshape for multifingered robot hand grasping, given object under a manipulation task.  ...  In addition, Gorce and Rezzoug 14 propose a heuristic approach for hand posture configuration using neural networks for inverse kinematics and reinforcement learning in order to optimize hand position  ... 
doi:10.2991/ijcis.2010.3.5.14 fatcat:firrop5wkrgb5g4thk6tltdhqm

Transferring knowledge as heuristics in reinforcement learning: A case-based approach

Reinaldo A.C. Bianchi, Luiz A. Celiberto, Paulo E. Santos, Jackson P. Matsuura, Ramon Lopez de Mantaras
2015 Artificial Intelligence  
The goal of this paper is to propose and analyse a transfer learning meta-algorithm that allows the implementation of distinct methods using heuristics to accelerate a Reinforcement Learning procedure  ...  The results attest that our transfer learning algorithm outperforms recent heuristically-accelerated reinforcement learning and transfer learning algorithms.  ...  [26] propose a transfer-learning method for a model-based reinforcement learning algorithm for continuous state space.  ... 
doi:10.1016/j.artint.2015.05.008 fatcat:zrxiey6sojg2lfxr37uca4owae

Multicast Tree Generation using Meta Reinforcement Learning in SDN-based Smart Network Platforms

2021 KSII Transactions on Internet and Information Systems  
In this paper, we propose a new multicast tree generation algorithm which produces a multicast tree using an agent trained by model-based meta reinforcement learning.  ...  Accordingly, the demand for a technology for efficiently delivering multimedia traffic is also constantly increasing.  ...  Model-based meta reinforcement learning comprises outer-loop training for learning a new environment, and inner-loop training for achieving a goal in a selected environment.  ... 
doi:10.3837/tiis.2021.09.003 fatcat:2fwewmcwrfgd7hla3uume3bkd4

Virtual and intelligent traffic signs in rescue simulation system: Imitation of human society in agent society

Mostafa Asghari, Behrooz Masoumi, Mohammad Reza Meybodi
2009 2009 IEEE International Symposium on Computational Intelligence in Robotics and Automation - (CIRA)  
Now, there are some techniques called machine learning, and reinforcement learning is one of the machine learning which often used for actual machine.  ...  The pocket robot partner ...expandSECTION: Evolutionary conpution 1A meta-heuristic paradigm for solving the forward kinematics of 6-6 general parallel manipulator Rohitash Chandra, Marcus Frean, Luc Rolland  ...  By means of using the competitive associative net caUed CAN2 for plane extraction, we constructed two methods: one is for the ..  ... 
doi:10.1109/cira.2009.5423206 dblp:conf/cira/AsghariMM09 fatcat:r5aq3mrpuvd7zdnf3ju7rflzrq

Multi-Objective Learning Automata for Design and Optimization a Two-Stage CMOS Operational Amplifier

N. Sayyadi Shahraki, S. H. Zahiri
2020 Iranian Journal of Electrical and Electronic Engineering  
In this paper, we propose an efficient approach to design optimization of analog circuits that is based on the reinforcement learning method.  ...  The workability of the proposed approach is evaluated in comparison with the most well-known category of intelligent meta-heuristic Multi-Objective Optimization (MOO) methods such as Particle Swarm Optimization  ...  So, the meta-heuristic approaches are the best candidate for solving them.  ... 
doaj:f6c228860d9f45d28102dce308a35e10 fatcat:7ficgi4jb5gd5dwyjcmr3bislq

Hierarchical reinforcement learning as creative problem solving

Thomas R. Colin, Tony Belpaeme, Angelo Cangelosi, Nikolas Hemion
2016 Robotics and Autonomous Systems  
We draw a parallel between the properties of insight according to psychology and the properties of Hierarchical Reinforcement Learning (HRL) systems for embodied agents.  ...  h i g h l i g h t s • Reinforcement learning's option switches are analogous to psychological insight. • Insight and options reveal comparable capabilities for transformational creativity. • Open problems  ...  We would like to thank Paul Baxter for the valuable input to this work.  ... 
doi:10.1016/j.robot.2016.08.021 fatcat:bppumzzwkvcx3e4tssbtl7ozmu

Understanding TSP Difficulty by Learning from Evolved Instances [chapter]

Kate Smith-Miles, Jano van Hemert, Xin Yu Lim
2010 Lecture Notes in Computer Science  
be learned is needed.  ...  This paper provides a methodology to determine if the meta-data is sufficient, and demonstrates the critical role played by instance generation methods.  ...  Once we have sufficient meta-data, we can apply machine learning methods to learn the relationships within the meta-data.  ... 
doi:10.1007/978-3-642-13800-3_29 fatcat:mgowrkd2ibgajfvhrn4bx2hf64

Designing an AI-Based Adaptive Controller Augmented with a System Identifier for a Micro-Class Robot Equipped with a Vibrating Actuator [article]

AmirReza BabaAhmadi, Nima Naseri
2022 arXiv   pre-print
Using this method, several specific paths for the movement of this micro robot are simulated.  ...  Based on the simulation results, the proposed controlling strategy guarantees acceptable performance for tracking different paths due to plotted near-zero errors and handles the nonlinear behavior of the  ...  This research received no specific grant from any funding agency, commercial or not-for-profit sectors Declaration of competing interest The authors declare that they have no known competing financial  ... 
arXiv:2204.08541v1 fatcat:c2msgjhqmvfalmean2spyrylde

Artificial Intelligence and Its Application in Optimization under Uncertainty [chapter]

Saeid Sadeghi, Maghsoud Amiri, Farzaneh Mansoori Mooseloo
2021 Artificial Intelligence  
Perspectives on reinforcement learning (RL)-based data-driven optimization and deep RL for solving NP-hard problems are discussed.  ...  This chapter also identifies fertile avenues for future research that focus on deep-data-driven optimization, deep data-driven models, as well as online learning-based data-driven optimization.  ...  The developed meta-algorithm automatically learns good heuristics for a diverse range of optimization problems over graphs. Mosadegh et al.  ... 
doi:10.5772/intechopen.98628 fatcat:mtbuaqghgvha3fa64osyahca2q

Machine Learning for Combinatorial Optimization: a Methodological Tour d'Horizon [article]

Yoshua Bengio and Andrea Lodi and Antoine Prouvost
2020 arXiv   pre-print
Given the hard nature of these problems, state-of-the-art algorithms rely on handcrafted heuristics for making decisions that are otherwise too expensive to compute or mathematically not well defined.  ...  We advocate for pushing further the integration of machine learning and combinatorial optimization and detail a methodology to do so.  ...  endless discussions on the subject and for reading and commenting a preliminary version  ... 
arXiv:1811.06128v2 fatcat:sslxegsjszfl7dvohv3253fyru

Aircraft Type Identification Using Reinforcement Active Learning

Hong-lan HUANG, Ruo-tong LIAO, Li CHEN, Kui-hua HUANG, Yang-he FENG, Jin-cai HUANG, Ze-yi LIU, Jia-rui ZHANG
2019 DEStech Transactions on Computer Science and Engineering  
Based on this, we employ a learning-based approach which combines active learning with reinforcement learning to learn how and when to request labels for the aircraft type recognition problem.  ...  As a subclass of Automatic Target Recognition problem, Automatic Aircraft Recognition plays an important role in air traffic management and modern battlefield for automatic monitoring and detection.  ...  Different from engineered selection heuristics, we introduce a model learning active learning algorithms end-to-end in an reinforcement learning way.  ... 
doi:10.12783/dtcse/iteee2019/28740 fatcat:cewh5xdxe5cbznafxezi5tju2u

An improved meta-heuristic approach to extraction sequencing and block routing

Y.A. Sari
2016 Journal of the Southern African Institute of Mining and Metallurgy  
In this paper, a new approach based on a meta-heuristic is proposed. Meta-heuristic approaches use processing, inference, and memory at the same time in order to learn how to improve the solution.  ...  Different meta-heuristic techniques and their applications to mine production scheduling are discussed.  ...  Reinforcement learning is similar to SA and genetic algorithms in terms of being an algorithm for searching the parameter space using the concept of reward; which in our case will be the improvement in  ... 
doi:10.17159/2411-9717/2016/v116n7a9 fatcat:3ede2cfyejborj6f5kmgu6sujq

Learning to Optimise General TSP Instances [article]

Nasrin Sultana, Jeffrey Chan, A. K. Qin, Tabinda Sarwar
2020 arXiv   pre-print
Deep learning has been successfully extended to meta-learning, where previous solving efforts assist in learning how to optimise future optimisation instances.  ...  to learn from, which can be time-consuming and difficult to find reasonable solutions for harder TSP instances.  ...  Acknowledgements The authors wish to thank Kendall Taylor for his valuable comments and helpful suggestions for figures which greatly improved the paper's quality.  ... 
arXiv:2010.12214v2 fatcat:mcsrqb4vqvhkpn76zwg4bnrb4q

A comparative analysis of the travelling salesman problem: Exact and machine learning techniques

Jeremiah Ishaya, Department of Mathematical Science, African Institute for Mathematical Sciences, Mbour, Senegal, Abdullahi Ibrahim, Nassirou Lo, Department of Mathematical Science, Baze University Abuja, Nigeria, Department of Mathematical Science, African Institute for Mathematical Sciences, Mbour, Senegal
2019 Open Journal of Discrete Applied Mathematics  
In the machine learning method, we used neural networks and reinforcement learning with 2-opt to train a recurrent network that predict a distribution of different location permutations using the negative  ...  This paper studied two methods: branch-and-cut and machine learning methods.  ...  Acknowledgments: We appreciate African Institute for Mathematical Science, Senegal for full funding in order to carry out this research at AIMS.  ... 
doi:10.30538/psrp-odam2019.0020 fatcat:7cpznvgsvnbs5dbfhqrjqctrhq

Learning Combinatorial Optimization on Graphs: A Survey with Applications to Networking

Natalia Vesselinova, Rebecca Steinert, Daniel F. Perez-Ramirez, Magnus Boman
2020 IEEE Access  
Relevant developments in machine learning research on graphs are surveyed for this purpose.  ...  We organize and compare the structures involved with learning to solve combinatorial optimization problems, with a special eye on the telecommunications domain and its continuous development of live and  ...  Junaid Shuja, who coordinated the review process, and to the anonymous reviewers for their expeditious and helpful review comments received in preparation of the final version of the manuscript.  ... 
doi:10.1109/access.2020.3004964 fatcat:v7i7x6p77zfi7dntipxoiolily
« Previous Showing results 1 — 15 out of 3,275 results