Genetic programming for the minimum time swing up and balance control acrobot problem

Dracopoulos, D. and Nichols, B.D. 2017. Genetic programming for the minimum time swing up and balance control acrobot problem. Expert Systems. 34 (5), p. e12115 e12115. https://doi.org/10.1111/exsy.12115

TitleGenetic programming for the minimum time swing up and balance control acrobot problem
AuthorsDracopoulos, D. and Nichols, B.D.
Abstract

This work describes how genetic programming is applied to evolving controllers for the minimum time swing up and inverted balance tasks of the continuous state and action: limited torque acrobot. The best swing-up controller is able to swing the acrobot up to a position very close to the inverted ‘handstand’ position in a very short time, shorter than that of Coulom (2004), who applied the same constraints on the applied torque values, and to take only slightly longer than the approach by Lai et al. (2009) where far larger torque values were allowed. The best balance controller is able to balance the acrobot in the inverted position when starting from the balance position for the length of time used in the fitness function in all runs; furthermore, 47 out of 50 of the runs evolve controllers able to maintain the balance position for an extended period, an improvement on the balance controllers generated by Dracopoulos and Nichols (2012), which this paper is extended from. The most successful balance controller is also able to balance the acrobot when starting from a small offset from the balance position for this extended period.

Keywordsartificial intelligence, control systems, genetic programming, computational intelligence
Article numbere12115
JournalExpert Systems
Journal citation34 (5), p. e12115
ISSN1468-0394
Year2017
PublisherWiley
Digital Object Identifier (DOI)https://doi.org/10.1111/exsy.12115
Publication dates
Published in printOct 2017
Published06 Jul 2015
Published online06 Jul 2015

Related outputs

A Better Predictor of Marathon Race Times based on Neural Networks
Dracopoulos, D. 2017. A Better Predictor of Marathon Race Times based on Neural Networks. Bramer, M. and Petridis, M. (ed.) 37th SGAI International Conference on Artificial Intelligence, AI 2017. Cambridge, UK 12 - 14 Dec 2017 Springer. https://doi.org/10.1007/978-3-319-71078-5

Application of Newton's Method to action selection in continuous state- and action-space reinforcement learning
Nichols, B.D. and Dracopoulos, D. 2014. Application of Newton's Method to action selection in continuous state- and action-space reinforcement learning. in: ESANN 2014 proceedings, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. Bruges (Belgium), 23-25 April 2014 D facto.

Reinforcement learning in continuous state- and action-space
Nichols, B.D. 2014. Reinforcement learning in continuous state- and action-space. PhD thesis University of Westminster Faculty of Science and Technology https://doi.org/10.34737/967w8

Genetic programming as a solver to challenging reinforcement learning problems
Dracopoulos, D., Effraimidis, D. and Nichols, B.D. 2013. Genetic programming as a solver to challenging reinforcement learning problems. International Journal of Computer Research. 20 (3), pp. 351-379.

Genetic programming as a solver to challenging reinforcement learning problems
Dracopoulos, D., Effraimidis, D. and Nichols, B.D. 2013. Genetic programming as a solver to challenging reinforcement learning problems. in: Clary, T.S. (ed.) Horizons in computer science research Hauppauge, NY Nova Science Publishers.

Swing up and balance control of the acrobot solved by genetic programming
Dracopoulos, D. and Nichols, B.D. 2012. Swing up and balance control of the acrobot solved by genetic programming. in: Bramer, M. and Petridis, M. (ed.) Research and Development in Intelligent Systems XXIX: Incorporating Applications and Innovations in Intelligent Systems XX Proceedings of AI-2012, The 32nd SGAI International Conference on Innovative Techniques & Applications of Artificial Intelligence London Springer. pp. 229-242

Genetic programming for generalised helicopter hovering control
Dracopoulos, D. and Effraimidis, D. 2012. Genetic programming for generalised helicopter hovering control. in: Moraglio, A., Silva, S., Krawiec, K., Machado, P. and Cotta, C. (ed.) Genetic programming: proceedings of the 15th European conference, EUROGP 2012 Malaga, Spain Springer.

Bioreactor control by genetic programming
Dracopoulos, D. and Piccoli, R. 2011. Bioreactor control by genetic programming. in: Schaefer, R., Cotta, C., Kolodziej, J. and Rudolph, G. (ed.) Parallel Problem Solving from Nature – PPSN XI: 11th International Conference, Kraków, Poland, September 11-15, 2010. Proceedings, part II Berlin Heidelberg Springer.

Genetic evolution of controllers for challenging control problems
Dracopoulos, D. 2011. Genetic evolution of controllers for challenging control problems. Journal of Computational Methods in Science and Engineering. 11 (4), pp. 227-242. https://doi.org/10.3233/JCM-2011-0388

Bioreactor control based on evolutionary computing and neural dynamic programming
Dracopoulos, D. 2011. Bioreactor control based on evolutionary computing and neural dynamic programming. in: Antolli, P.G. and Liu, Z. (ed.) Bioreactors: design, properties, and applications Nova Science Publishers. pp. 179-198

Evolutionary learning
Dracopoulos, D. 2009. Evolutionary learning. in: Wah, B.W. and Woeltge, F.W. (ed.) Wiley encyclopedia of computer science and engineering Chichester Wiley.

Autolanding of commercial aircrafts by genetic programming
Dracopoulos, D. 2007. Autolanding of commercial aircrafts by genetic programming. in: Ao, S.I., Gelman, L., Hukins, D.W.L., Hunter, A. and Korsunsky, A.M. (ed.) Proceedings of the World Congress on Engineering, WCE 2007, London, UK, 2-4 July, 2007 International Association of Engineers/Newswood Limited.

Evolutionary learning
Dracopoulos, D. 2006. Evolutionary learning. in: Wiley encyclopedia of computer science and engineering Chichester, UK Wiley.

Robot Path Planning for Maze Navigation
Dracopoulos, D. 1998. Robot Path Planning for Maze Navigation. 1998 World Congress on Computational Intelligence-International Joint Conference on Neural Networks (IJCNN'98). Anchorage, Alaska, USA 04 - 09 May 1998 IEEE . https://doi.org/10.1109/IJCNN.1998.687180

Neural Robot Path Planning: The Maze Problem
Dracopoulos, D. 1998. Neural Robot Path Planning: The Maze Problem. Neural Computing & Applications. 7 (2), pp. 115-120. https://doi.org/10.1007/BF01414163

Guest editorial: Neural Networks for Machine Vision
Dracopoulos, D. and Rosin, P.L. 1998. Guest editorial: Neural Networks for Machine Vision. Neural Computing & Applications. 7 (3), p. 194. https://doi.org/10.1007/BF01414881

Genetic Detumbling a Satellite
Dracopoulos, D. 1997. Genetic Detumbling a Satellite. Lyon, France Ecole Normale Superieure de Lyon, Laboratoire de Informatique du Parallelisme.

Genetic Algorithms and Genetic Programming for Control
Dracopoulos, D. 1997. Genetic Algorithms and Genetic Programming for Control. in: Dasgupta, D. and Michalewicz, Z. (ed.) Evolutionary Algorithms in Engineering Applications Berlin Heidelberg Springer. pp. 329-343

Evolutionary control of a Satellite
Dracopoulos, D. 1997. Evolutionary control of a Satellite. Second International Conference on Genetic Programming. Stanford University, USA 13 - 16 Jul 1997 Morgan Kaufmann.

Finding patterns and subfamilies in biosequences by genetic programming
Brazma, A. and Dracopoulos, D. 1997. Finding patterns and subfamilies in biosequences by genetic programming. 1997 SIAM Annual Meeting. Stanford, California, USA 14 - 18 Jul 1997

A comparison of artificial intelligence techniques for the identification of people at high risk of oral cancer
Elliot, C., Kent, S., Hammond, P., Dracopoulos, D., Downer, M.C. and Speight, P.M. 1997. A comparison of artificial intelligence techniques for the identification of people at high risk of oral cancer. 44th Annual General Meeting of the British Society for Dental Research. Brighton, UK 07 - 10 Apr 1997

A comparison of artificial intelligence techniques for the identification of people at high risk of oral cancer
Elliott, C., Kent, S., Hammond, P., Dracopoulos, D., Downer, M.C. and Speight, P.M. 1997. A comparison of artificial intelligence techniques for the identification of people at high risk of oral cancer. Journal of Dental Research. 76 (5), p. 1053. https://doi.org/10.1177/00220345970760050101

Genetic Programming for Prediction and Control
Dracopoulos, D. and Kent, S. 1997. Genetic Programming for Prediction and Control. Neural Computing & Applications. 6 (4), pp. 214-228. https://doi.org/10.1007/BF01501508

Neurocontrol: Recent advances and links with the Human Brain
Dracopoulos, D. 1997. Neurocontrol: Recent advances and links with the Human Brain. AI & Society. 11 (4), pp. 63-75. https://doi.org/10.1007/BF02812439

Adaptive Neuro-Genetic Control of Chaos applied to the Attitude Control Problem
Dracopoulos, D. and Jones, A.J. 1997. Adaptive Neuro-Genetic Control of Chaos applied to the Attitude Control Problem. Neural Computing & Applications. 6 (2), pp. 102-115. https://doi.org/10.1007/BF01414007

Evolutionary Learning Algorithms for Neural Adaptive Control
Dracopoulos, D. 1997. Evolutionary Learning Algorithms for Neural Adaptive Control. Springer.

Bulk Synchronous Parallelisation of Genetic Programming
Kent, S. and Dracopoulos, D. 1996. Bulk Synchronous Parallelisation of Genetic Programming. Brunel University.

Adaptive neuro-genetic control of chaos applied to the attitude control problem
Dracopoulos, D. 1996. Adaptive neuro-genetic control of chaos applied to the attitude control problem. Brunel University.

Evolutionary Neurocontrol of Chaos and the Attitude Control Problem
Dracopoulos, D. 1996. Evolutionary Neurocontrol of Chaos and the Attitude Control Problem. in: Taylor, J.G. (ed.) Neural Networks and their Applications Wiley.

Speeding up Genetic Programming: A parallel implementation using BSP
Dracopoulos, D. and Kent, S. 1996. Speeding up Genetic Programming: A parallel implementation using BSP. Koza, J.R. (ed.) First International Conference on Genetic Programming. Stanford, California, USA 28 - 31 Jul 1996 MIT Press.

Parallel Genetic Programming
Dracopoulos, D. and Self, D. 1996. Parallel Genetic Programming. Jesshope, C. and Shafarenko, S. (ed.) UK Parallel '96. 03 - 05 Jul 1996 Springer. https://doi.org/10.1007/978-1-4471-1504-5_11

Bulk Synchronous Parallelisation of Genetic Programming
Dracopoulos, D. and Kent, S. 1996. Bulk Synchronous Parallelisation of Genetic Programming. Waśniewski J., Dongarra J., Madsen K. and Olesen D. (ed.) Applied parallel computing : industrial strength computation and optimization ; Proceedings of the third International Workshop (PARA'96). Lyngby, Denmark 18 - 21 Aug 1996 Springer. https://doi.org/10.1007/3-540-62095-8_23

An Adaptive Neurocontrol Design applied to the Attitude Control Problem
Dracopoulos, D. and Jones, A.J. 1994. An Adaptive Neurocontrol Design applied to the Attitude Control Problem. Rogers, S.K. and Ruck, D.W. (ed.) Applications of Neural Networks V, OE/Aerospace Sensing. Orlando, USA 05 - 08 Apr 1994 SPIE. https://doi.org/10.1117/12.169987

Neural Networks and Genetic Algorithms for the Attitude Control Problem
Dracopoulos, D. and Jones, A.J. 1994. Neural Networks and Genetic Algorithms for the Attitude Control Problem. Neural Networks and their Cognitive and Industrial Applications (NeuroNimes). Marseille, France 15 - 16 Dec 1994

Neuro-Genetic Adaptive Attitude Control
Dracopoulos, D. and Jones, A.J. 1994. Neuro-Genetic Adaptive Attitude Control. Neural Computing & Applications. 2 (4), pp. 183-204. https://doi.org/10.1007/BF01414807

Modeling Dynamic Systems
Dracopoulos, D. and Jones, A.J. 1993. Modeling Dynamic Systems. First World Congress on Neural Networks Proceedings. Lawrence Erlbaum.

Neuromodels of Analytic Dynamic Systems
Dracopoulos, D. and Jones, A.J. 1993. Neuromodels of Analytic Dynamic Systems. Neural Computing & Applications. 1 (4), pp. 268-279. https://doi.org/10.1007/BF02098745

The Connection Machine Implementation and Programming
Dracopoulos, D. 1992. The Connection Machine Implementation and Programming. London Imperial College.

Permalink - https://westminsterresearch.westminster.ac.uk/item/99853/genetic-programming-for-the-minimum-time-swing-up-and-balance-control-acrobot-problem


Share this

Usage statistics

140 total views
0 total downloads
These values cover views and downloads from WestminsterResearch and are for the period from September 2nd 2018, when this repository was created.