Improvement on Supporting Machine Learning Algorithm for Solving Problem in Immediate Decision Making

Abdolkarim Niazi; Norizah Redzuan; Raja Ishak Raja Hamzah; Sara Esfandiari

doi:10.4028/www.scientific.net/AMR.566.572

Paper Titles

Design of Bulldozer’s Remote Monitoring Service System Based on GPS
p.552

Process Research of Laser Variable-Spot Overlap Cladding Based on Inside-Laser Coaxial Powder Feeding
p.556

Design and Evaluation of Bupt-Cloud-Storage System
p.560

Study of Remote Fault Diagnosis System to Wind Generator Gearbox Based on DSP
p.568

Improvement on Supporting Machine Learning Algorithm for Solving Problem in Immediate Decision Making
p.572

Exploratory Research on Earnings Forecast Model-Based on Chinese Manufacturing Companies
p.580

Research on the Access-Authorizing-Problem in a Collaborative Manufacturing Platform
p.584

Model and Heuristic Algorithm for Steel Productive Resources Balance Problem
p.591

High Birefringence and Negative Dispersion Effect of Hybrid-Core Photonic Crystal Fiber
p.599

HomeAdvanced Materials ResearchAdvanced Materials Research Vol. 566Improvement on Supporting Machine Learning...

Improvement on Supporting Machine Learning Algorithm for Solving Problem in Immediate Decision Making

Abstract:

In this paper, a new algorithm based on case base reasoning and reinforcement learning (RL) is proposed to increase the convergence rate of the reinforcement learning algorithms. RL algorithms are very useful for solving wide variety decision problems when their models are not available and they must make decision correctly in every state of system, such as multi agent systems, artificial control systems, robotic, tool condition monitoring and etc. In the propose method, we investigate how making improved action selection in reinforcement learning (RL) algorithm. In the proposed method, the new combined model using case base reasoning systems and a new optimized function is proposed to select the action, which led to an increase in algorithms based on Q-learning. The algorithm mentioned was used for solving the problem of cooperative Markov’s games as one of the models of Markov based multi-agent systems. The results of experiments Indicated that the proposed algorithms perform better than the existing algorithms in terms of speed and accuracy of reaching the optimal policy.

You might also be interested in these eBooks

Machine Design and Manufacturing Engineering

View Preview

Info:

Periodical:

Advanced Materials Research (Volume 566)

Pages:

572-579

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.566.572

Citation:

Cite this paper

Online since:

September 2012

Authors:

Abdolkarim Niazi, Norizah Redzuan, Raja Ishak Raja Hamzah, Sara Esfandiari

Keywords:

Machine Learning (ML), Multi-Agent System (MAS), Reinforcement Learning, Tool Condition Monitoring

Export:

RIS, BibTeX

Price:

Permissions:

Request Permissions

References

[1] R. A. C. Bianchi, C. H. C. Ribeiro, A. H. R. Costa, Accelerating autonomous learning by using a heuristic selection of actions, Journal of Heuristis, 2008, Vol. 2, pp.135-168.

DOI: 10.1007/s10732-007-9031-5

Google Scholar

[2] R. A. C. Bianchi, C. H. C. Ribeiro, A. H. R. Costa, Heuristic selection of actions in multi agent reinforcement learning, 20th International conference on Artificial Intelligence, India , Jan 2007, pp.690-695.

Google Scholar

[3] M. Lauer and M. Riedmiller, An Algorithm for Distributed Reinforcement Learning in Cooperative Multi-Agent Systems, in The 17th International Conference on Machine Learning San Francisco, CA, USA, 2000: Morgan Kaufmann Publishers Inc, p.535 – 542.

Google Scholar

[4] A. G. Barto and R. S. Sutton, Reinforcement Learning: an introduction, MIT Press, Cambridge, MA, 1998‏.

Google Scholar

[5] X. Wang and T. Sandholm, Reinforcement Learning to Play an Optimal Nash Equilibrium in Team Markov Games, in Advances in Neural Information Processing Systems, 2002, vol. 15: MIT Press, pp.1571-1578, (2002).

Google Scholar

[6] F. S. Melo, M. I. Ribeiro, Reinforcement Learning with Function Approximation for Cooperative Navigation Tasks, IEEE International Conference on Robotics and A Utomation Pasadena, CA, USA, May 2008, pp.3321-2237.

DOI: 10.1109/robot.2008.4543717

Google Scholar

[7] M. Lauer and M. Riedmiller, Reinforcement Learning for Stochastic cooperative Multi-agent Systems, In Proceeding of AAMAS 2004, New York, NY, ACM Press, pp.1514-1515.

Google Scholar

[8] Gabel, T. And Riedmiller, M., CBR for state value function Approximation in Reinforcement Learning, Proceeding of the Inter. Conference on Case Based Learning 2005 (ICCBR 2005) , Springer , Chicago, USA.

DOI: 10.1007/11536406_18

Google Scholar

[9] J. Hu, M. Wellman, Nash Q-Learning for General-Sum Stochastic Games, Journal of Machine Learning Research, , 2003, vol. 4, pp.1039-1069.

Google Scholar