Learning agents' reliability through Bayesian Conditioning: A simulation experiment

1997 ◽  
pp. 151-167 ◽  
Author(s):  
Aldo Franco Dragoni ◽  
Paolo Giorgini
Keyword(s):  
Simulation Experiment ◽  
Learning Agents ◽  
Bayesian Conditioning

Determination of Optimum Parameters for Anaerobic Thermophilic Bacterium Injection using Commercial Simulator: Core Flooding Validation and Sensitivity

2020 ◽  
Author(s):  
A. Koto
Keyword(s):  
Oil Recovery ◽  
Simulation Experiment ◽  
Previous Experiment ◽  
Core Sample ◽  
Thermophilic Bacterium ◽  
Injection Rate ◽  
Core Flooding ◽  
Optimum Parameters ◽  
Result Show

The objective of this paper is to determine the optimum anaerobic-thermophilic bacterium injection (Microbial Enhanced Oil Recovery) parameters using commercial simulator from core flooding experiments. From the previous experiment in the laboratory, Petrotoga sp AR80 microbe and yeast extract has been injected into core sample. The result show that the experiment with the treated microbe flooding has produced more oil than the experiment that treated by brine flooding. Moreover, this microbe classified into anaerobic thermophilic bacterium due to its ability to live in 80 degC and without oxygen. So, to find the optimum parameter that affect this microbe, the simulation experiment has been conducted. The simulator that is used is CMG – STAR 2015.10. There are five scenarios that have been made to forecast the performance of microbial flooding. Each of this scenario focus on the injection rate and shut in periods. In terms of the result, the best scenario on this research can yield an oil recovery up to 55.7%.

Pengembangan Pembelajaran Model Blended Computer Based Learning (BCBL) Tentang Turunan Fungsi untuk Meningkatkan Kemandirian Belajar Siswa SMA

2019 ◽  
Vol 2 ◽  
Author(s):  
M. Safrudin ◽  
Sutaryat Trisnamansyah ◽  
Tb. Abin Syamsuddin Makmun ◽  
Deni Darmawan
Keyword(s):  
High Schools ◽  
Simulation Experiment ◽  
Computer Assisted ◽  
Development Stages ◽  
Computer Based Learning ◽  
Self Reliance ◽  
Computer Based ◽  
Systematic Development ◽  
Learner Activity

The aimed of this studied was developed learning through computer-assisted as BCBL. Result of this studied have been stated that: (a) the potential of five high schools in Karawang districts supported the implementation of BCBL development, (b) planning of BCBL development through a systematic development stages from preparation, production, simulation, experiment, and publication, (c) the implementation result of BCBL learning through revision tested were learner activity and higher autonomy. Keywords: BCBL; Independence Self-reliance; Student Competence.

A Novel Transmitting System for Electromagnetic Sounding Based on Tri-state Boost Converter

2019 ◽  
Vol 12 (6) ◽  
pp. 494-499
Author(s):  
Gang Li ◽  
Binren Zhang
Keyword(s):  
Simulation Model ◽  
Output Power ◽  
Basic Principle ◽  
Simulation Experiment ◽  
Dynamic Performance ◽  
Boost Converter ◽  
Electromagnetic Sounding ◽  
Important Method ◽  
Geophysical Exploration ◽  
Electromagnetic Detection

Background: Electromagnetic detection is an important method of geophysical exploration. The transmitting system is an important part of the electromagnetic detection equipment. Methods: The general topologies of a transmitting system for EM instrument are analyzed. The basic principle of EM detection is interpreted. In order to improve the output power and give consideration to the dynamic performance, an electromagnetic transmitting system based on the tri-state boost converter is proposed in this paper. Results: The principle of the proposed transmitting system is analyzed. The topology of the proposed transmitting system is illustrated and the working modes of tri-state boost converter are given. Conclusion: The simulation model is established and the simulation experiment is carried out to verify the feasibility of the new electromagnetic transmitting system.

A Defense Mechanism Based on Improved Allocation Strategy of VMs Co-Resident Attack in Power Cloud Platform

2020 ◽  
Vol 13 ◽  
Author(s):  
Yuancheng Li ◽  
Pan Zhang ◽  
Daoxing Li ◽  
Jing Zeng
Keyword(s):  
Virtual Machine ◽  
Simulation Experiment ◽  
Virtual Machines ◽  
Defense Mechanism ◽  
Security Threats ◽  
Allocation Strategy ◽  
Cloud Platform ◽  
Deployment Strategy ◽  
Dbscan Algorithm ◽  
Maximum Minimum

Background: Cloud platform is widely used in electric power field. Virtual machine co-resident attack is one of the major security threats to the existing power cloud platform. Objective: This paper proposes a mechanism to defend virtual machine co-resident attack on power cloud platform. Method: Our defense mechanism uses the DBSCAN algorithm to classify and output the classification results through the random forest and uses improved virtual machine deployment strategy which combines the advantages of random round robin strategy and maximum/minimum resource strategy to deploy virtual machines. Results: we made a simulation experiment on power cloud platform of State Grid and verified the effectiveness of proposed defense deployment strategy. Conclusion: After the virtual machine deployment strategy is improved, the coverage of the virtual machine is remarkably reduced which proves that our defense mechanism achieves some effect of defending the virtual machine from virtual machine co-resident attack.

Research on Quick Superplastic Forming for Aluminium Alloy Sheet

2012 ◽  
Vol 735 ◽  
pp. 301-306 ◽  
Author(s):  
Hai Jian Liang ◽  
Xiao Wei Wu ◽  
Yong Wang ◽  
Quan Lin Jin ◽  
Zhao Li Ma ◽  
...  
Keyword(s):  
Mass Production ◽  
Simulation Experiment ◽  
Hot Stamping ◽  
Superplastic Forming ◽  
Alloy Sheet ◽  
High Rate ◽  
Hot Forming ◽  
Forming Technology ◽  
Complex Process ◽  
Better Than

This article describes the high rate superplastic forming. The high rate superplastic forming technology is a new complex process,which integrates hot stamping and superplastic forming .It has feature of rapidity of the hot stamping and character of excellent formability of the superplastic forming.We obtained the best proportion of the hot forming and the superplastic forming through simulation experiment, and formed a car’s abonnet by applying the proportion.Compared with the high rate superplastic forming,the forming quality is better than that of hot forming. and the forming time is less than that of superplastic forming. Result shows that ,the high rate superplastic forming technology can meet the requirements for mass production.

scholarly journals An Evaluation Methodology for Interactive Reinforcement Learning with Simulated Users

Biomimetics ◽  
2021 ◽  
Vol 6 (1) ◽  
pp. 13
Author(s):  
Adam Bignold ◽  
Francisco Cruz ◽  
Richard Dazeley ◽  
Peter Vamplew ◽  
Cameron Foale
Keyword(s):  
Reinforcement Learning ◽  
Information Source ◽  
Human Interaction ◽  
Evaluation Methodology ◽  
External Information ◽  
Preliminary Evaluation ◽  
Learning Agents ◽  
Learning Agent ◽  
Knowledge Bias ◽  
The Impact

Interactive reinforcement learning methods utilise an external information source to evaluate decisions and accelerate learning. Previous work has shown that human advice could significantly improve learning agents’ performance. When evaluating reinforcement learning algorithms, it is common to repeat experiments as parameters are altered or to gain a sufficient sample size. In this regard, to require human interaction every time an experiment is restarted is undesirable, particularly when the expense in doing so can be considerable. Additionally, reusing the same people for the experiment introduces bias, as they will learn the behaviour of the agent and the dynamics of the environment. This paper presents a methodology for evaluating interactive reinforcement learning agents by employing simulated users. Simulated users allow human knowledge, bias, and interaction to be simulated. The use of simulated users allows the development and testing of reinforcement learning agents, and can provide indicative results of agent performance under defined human constraints. While simulated users are no replacement for actual humans, they do offer an affordable and fast alternative for evaluative assisted agents. We introduce a method for performing a preliminary evaluation utilising simulated users to show how performance changes depending on the type of user assisting the agent. Moreover, we describe how human interaction may be simulated, and present an experiment illustrating the applicability of simulating users in evaluating agent performance when assisted by different types of trainers. Experimental results show that the use of this methodology allows for greater insight into the performance of interactive reinforcement learning agents when advised by different users. The use of simulated users with varying characteristics allows for evaluation of the impact of those characteristics on the behaviour of the learning agent.

Sign in / Sign up

Export Citation Format

Share Document