scholarly journals Creation and implementation of a set of game strategies based on training neural networks with reinforcement learning

2021 ◽  
Vol 2134 (1) ◽  
pp. 012005
Author(s):  
D S Kozlov ◽  
O N Polovikova
Keyword(s):  
Neural Networks ◽  
Reinforcement Learning ◽  
The Self ◽  
Learning Approach ◽  
Self Learning

Abstract The study explores the problems of reinforcement learning and finding non-obvious play strategies using reinforcement learning. Two approaches to agent training (blind and pattern-based) are considered and implemented. The advantage of the self-learning approach with reinforcement using patterns as applied to a specific game (tic-tac-toe five in a row) is shown. Recorded and analyzed the use of unusual strategies by an agent using a pattern-based approach.

scholarly journals ReLeQ : A Reinforcement Learning Approach for Automatic Deep Quantization of Neural Networks

IEEE Micro ◽  
2020 ◽  
Vol 40 (5) ◽  
pp. 37-45 ◽  
Author(s):  
Ahmed T. Elthakeb ◽  
Prannoy Pilligundla ◽  
Fatemehsadat Mireshghallah ◽  
Amir Yazdanbakhsh ◽  
Hadi Esmaeilzadeh
Keyword(s):  
Neural Networks ◽  
Reinforcement Learning ◽  
Learning Approach

scholarly journals On the Design of Tailored Neural Networks for Energy Harvesting Broadcast Channels: A Reinforcement Learning Approach

IEEE Access ◽  
2020 ◽  
Vol 8 ◽  
pp. 179678-179691
Author(s):  
Heasung Kim ◽  
Jungtai Kim ◽  
Wonjae Shin ◽  
Heecheol Yang ◽  
Nayoung Lee ◽  
...  
Keyword(s):  
Neural Networks ◽  
Reinforcement Learning ◽  
Energy Harvesting ◽  
Broadcast Channels ◽  
Learning Approach

scholarly journals Blended Learning Case Study: “New to the Leadership Role”

2019 ◽  
Vol 12 (2) ◽  
pp. 79
Author(s):  
Ruben Weiser
Keyword(s):  
Blended Learning ◽  
Learning Experience ◽  
Leadership Role ◽  
The Self ◽  
Working Environment ◽  
Learning Approach ◽  
Learning Program ◽  
Leadership Program ◽  
Face To Face ◽  
Self Learning

<p>The blended learning „Leadership Program“ is a clever combination of self-learning and face-to-face-teaching periods. Heart of the self-learning period are interactive exercises and multimedia eLearning videos. A moderator, who leads trough every section of the eLearning, ensures a strong involvement for the participants. With the help of valuable play scenes with real actors, the participants get encouraged to question their own behavior in daily business. In addition, there are graphically animated explainer videos and highly qualified interactive learning exercises.</p><p>The eLearnings contain also transfer-exercises, which empower participants to adapt new learning contents easily to their working environment and gain valuable experiences.</p><p>The blended learning “Leadership Program” contains, beside the eLearning videos, two face-to-face teaching periods. These periods are very important for the learning experience, because they put focus on self-reflection and refer to the transfer-exercises from the eLearnings. The trainer discusses with the participants their experiences, encourages them to share their findings from the self-learn period and provides feedback and advices. The face-to-face teaching is not about delivering knowledge, this happens during the self-learning period, it is about strengthen it.</p><p>In the blended learning approach, the trainer is a learning companion, who guides participants through the different learning periods. Therefore, the trainer is always available for guidance during the self-learning period. The participants can get back to them over phone or email. All trainers have a special certificate, which enables them to teach with our blended learning approach. They know all eLearnings and transfer-exercises very well. Furthermore, a trainer guideline was specially developed for every blended learning program. This is possible due to our cooperation with the training company “Pawlik”, which gives us the opportunity to work with 150 specialized and highly certified trainers.</p><p>Self-learning and face-to-face teaching periods are framed by webinars. In the first session the participants get a detailed overview about the blended learning approach and its structure. In addition, they have the opportunity to introduce their self and get to know each other. The blended learning journey ends with two coaching calls, where the trainer offers support to the participants, in case they struggle to put their learnings into practice.</p><p>Our blended learning “Leadership Program” can be booked over Pink University. There are no extra bookings required for the trainers.  It is structured in modules and can be adapted easily to customer needs.</p>

A Self-Learning Model for Cylinder Wakes Using Neural Networks

2002 ◽  
Author(s):  
G. Balasubramanian ◽  
D. J. Olinger ◽  
M. A. Demetriou
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Adaptive Estimation ◽  
Lattice Models ◽  
Spectral Element ◽  
The Self ◽  
Projection Algorithm ◽  
The Neural Network ◽  
Wake Patterns ◽  
Self Learning

Coupled map lattice models (CML) that combine a series of low-dimensional circle maps with a diffusion model have predicted qualitative features of the wake behind vibrating flexible cables. However, there are always unmodelled dynamics if a quantitative comparison is made with wake patterns obtained from laboratory or simulated wake flows. To overcome this limitation, self-learning features can be incorporated into the simple CML model to capture the unmodelled dynamics. The self-learning CML uses radial basis function neural networks as online approximators of the unmodelled dynamics. The neural network weights are adaptively varied using a combination of a multivariable least squares algorithm and a projection algorithm. The adaptive estimation scheme, derived from a new convective diffusive CML, seeks to precisely estimate the neural network weights at each timestep by mimimizing the error between the simulated and measured wake patterns. Studies of this approach are conducted using wake patterns from spectral element based NEKTAR simulations of freely vibrating cable wakes at Re = 100. It is shown that the neural network based self-learning CML precisely estimates the simulated wake patterns within several shedding cycles. The self-learning CML is also shown to be computationally efficient.

scholarly journals Deep learning-based question answering system for intelligent humanoid robot

2020 ◽  
Vol 7 (1) ◽  
Author(s):  
Widodo Budiharto ◽  
Vincent Andreas ◽  
Alexander Agung Santoso Gunawan
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Knowledge Base ◽  
Humanoid Robot ◽  
Question Answering ◽  
The Self ◽  
Learning Approach ◽  
Learning Capability ◽  
Question Answering Systems ◽  
Self Learning

Abstract Background The development of Intelligent Humanoid Robot focuses on question answering systems that can interact with people is very limited. In this research, we would like to propose an Intelligent Humanoid Robot with the self-learning capability for accepting and giving responses from people based on Deep Learning and Big Data knowledge base. This kind of robot can be used widely in hotels, universities, and public services. The Humanoid Robot should consider the style of questions and conclude the answer through conversation between robot and user. In our scenario, the robot will detect the user’s face and accept commands from the user to do an action. Findings The question from the user will be processed using deep learning, and the result will be compared to the knowledge base on the system. We proposed our Deep Learning approach, based on Recurrent Neural Network (RNN) encoder, Convolution Neural Network (CNN) encoder, with Bidirectional Attention Flow (BiDAF). Conclusions Our evaluation indicates that using RNN based encoder with BiDAF gives a higher score, than CNN encoder with the BiDAF. Based on our experiment, our model get 82.43% F1 score and the RNN based encoder will give a higher EM/F1 score than using the CNN encoder.

Sign in / Sign up

Export Citation Format

Share Document