Comparing Knowledge-Based Reinforcement Learning to Neural Networks in a Strategy Game | SpringerLink
Skip to main content
Springer Nature Link
Log in

Comparing Knowledge-Based Reinforcement Learning to Neural Networks in a Strategy Game

  • Conference paper
  • First Online:
Hybrid Artificial Intelligent Systems (HAIS 2020)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 12344))

Included in the following conference series:

  • 1228 Accesses

Abstract

The paper reports on an experiment, in which a Knowledge-Based Reinforcement Learning (KB-RL) method was compared to a Neural Network (NN) approach in solving a classical Artificial Intelligence (AI) task. In contrast to NNs, which require a substantial amount of data to learn a good policy, the KB-RL method seeks to encode human knowledge into the solution, considerably reducing the amount of data needed for a good policy. By means of Reinforcement Learning (RL), KB-RL learns to optimize the model and improves the output of the system. Furthermore, KB-RL offers the advantage of a clear explanation of the taken decisions as well as transparent reasoning behind the solution.

The goal of the reported experiment was to examine the performance of the KB-RL method in contrast to the Neural Network and to explore the capabilities of KB-RL to deliver a strong solution for the AI tasks. The results show that, within the designed settings, KB-RL outperformed the NN, and was able to learn a better policy from the available amount of data. These results support the opinion that Artificial Intelligence can benefit from the discovery and study of alternative approaches, potentially extending the frontiers of AI.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
¥17,985 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
JPY 3498
Price includes VAT (Japan)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
JPY 11439
Price includes VAT (Japan)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
JPY 14299
Price includes VAT (Japan)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. A. Houk, P.: A Strategic Game Playing Agent for FreeCiv. Master’s thesis, Northwestern University, Illinois, United States (2004)

    Google Scholar 

  2. Abdullah, M.S., Kimble, C., Benest, I., Paige, R.: Knowledge-based systems: a re-evaluation. J. Knowl. Manage. 10(3), 127–142 (2006)

    Article  Google Scholar 

  3. Akerkar, R., Sajja, P.: Knowledge-Based Systems, 1st edn. Jones and Bartlett Publishers Inc., Burlington (2009)

    Google Scholar 

  4. Arnold, F., Horvat, B., Sacks, A.M.: Freeciv learner : a machine learning project utilizing genetic algorithms. Interim Report. The University of Auckland, Game AI Group (2005)

    Google Scholar 

  5. Avram, G.: Empirical study on knowledge based systems. Electron. J. Inf. Syst. Eval. 8, 11–20 (2005)

    Google Scholar 

  6. Bologna, G., Hayashi, Y.: A comparison study on rule extraction from neural network ensembles, boosted shallow trees, and SVMs. Appl. Comput. Intell. Soft Comput. 2018, 1–20 (2018). https://doi.org/10.1155/2018/4084850

    Article  Google Scholar 

  7. Branavan, S.R.K., Silver, D., Barzilay, R.: Learning to Win by Reading Manuals in a Monte-Carlo Framework. CoRR abs/1401.5390 (2014)

    Google Scholar 

  8. Cannady, J.: Artificial neural networks for misuse detection. In: National Information Systems Security Conference, pp. 443–456 (1998)

    Google Scholar 

  9. Chandrasekaran, B., Swartout, W.: Explanations in knowledge systems: the role of explicit representation of design knowledge. IEEE Exp. 6, 47–49 (1991)

    Article  Google Scholar 

  10. Gilpin, L.H., Bau, D., Yuan, B.Z., Bajwa, A., Specter, M., Kagal, L.: Explaining explanations: an overview of interpretability of machine learning. In: 2018 IEEE 5th International Conference on Data Science and Advanced Analytics (DSAA), pp. 80–89 (2018)

    Google Scholar 

  11. Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, Cambridge (2016). http://www.deeplearningbook.org

  12. Haykin, S.: Neural Networks: A Comprehensive Foundation, 3rd edn. Prentice-Hall Inc., Upper Saddle River (2007)

    MATH  Google Scholar 

  13. Hinkelmann, K., Ahmed, S., Corradini, F.: Combining machine learning with knowledge engineering to detect fake news in social networks - a survey. In: AAAI Spring Symposium: Combining Machine Learning with Knowledge Engineering (2019)

    Google Scholar 

  14. Hinrichs, T., Forbus, K.: Toward higher-order qualitative representations. In: Proceedings of QR 2012 (2012)

    Google Scholar 

  15. Hinrichs, T., Forbus, K.: Analogical learning in a turn-based strategy game. In: IJCAI International Joint Conference on Artificial Intelligence, pp. 853–858 (12 2007)

    Google Scholar 

  16. Jones, J., Goel, A.: Knowledge organization and structural credit assignment. In: Proceedings of IJCAI-05 Workshop on Reasoning, Representation and Learning in Computer Games, Edinburgh, UK, August 2005

    Google Scholar 

  17. Jones, J., Goel, A.K.: Metareasoning for adaptation of classification knowledge. In: AAMAS (2009)

    Google Scholar 

  18. Jones, J., Parnin, C., Sinharoy, A., Rugaber, S., Goel, A.K.: Adapting game-playing agents to game requirements. In: Proceedings of Fifth AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (AIIDE-09), pp. 148–153 (2009)

    Google Scholar 

  19. Khalil, K.M., Abdel-Aziz, M., Nazmy, T.T., Salem, A.B.M.: Intelligent Techniques for Resolving Conflicts of Knowledge in Multi-agent Decision Support Systems. ArXiv abs/1401.4381 (2014)

    Google Scholar 

  20. Kołcz, A., Chowdhury, A., Alspector, J.: Data duplication: an imbalance problem? In: In: Proceedings of the ICML 2003 Workshop on Learning from Imbalanced Datasets (2003)

    Google Scholar 

  21. Kumar, R., Srivastava, S., Gupta, J.R., Mohindru, A.: Comparative study of neural networks for dynamic nonlinear systems identification. Soft Comput. 23(1), 101–114 (2019)

    Article  MATH  Google Scholar 

  22. Lécué, F.: On the role of knowledge graphs in explainable AI. In: Joint Proceedings of the 6th International Workshop on Dataset PROFlLing and Search & the 1st Workshop on Semantic Explainability co-located with the 18th International Semantic Web Conference (ISWC 2019), Auckland, New Zealand, 27 October 2019, p. 29 (2019)

    Google Scholar 

  23. Lucas, P.: Expert Systems. In: Kok, J.N. (ed.) Encyclopedia of Life Support Systems (EOLSS), pp. 328–356. Eolss Publishers, Paris (2009)

    Google Scholar 

  24. Mitrea, C., Lee, C., Wu, Z.: A comparison between neural networks and traditional forecasting methods: a case study. Int. J. Eng. Bus. Manage. 1 (2009). https://doi.org/10.5772/6777

  25. Muggleton, S., Raedt, L.D.: Inductive logic programming: theory and methods. J. Logic Program. 19(20), 629–679 (1994)

    Article  MathSciNet  MATH  Google Scholar 

  26. Navarro, H., Bennun, L.: Descriptive examples of the limitations of artificial neural networks applied to the analysis of independent stochastic data. Int. J. Comput. Eng. Technol. 5, 40–42 (2014)

    Google Scholar 

  27. Nechepurenko, L., Voss, V.: FreeCiv Games for the Experiment on Comparing Knowledge-Based Reinforcement Learning and Neural Networks in Strategic Games (2019)

    Google Scholar 

  28. Neches, R., Swartout, W.R., Moore, J.: Explainable (and maintainable) expert systems. In: Proceedings of the 9th International Joint Conference on Artificial Intelligence, IJCAI 1985, vol. 1, pp. 382–389. Morgan Kaufmann Publishers Inc., San Francisco (1985)

    Google Scholar 

  29. Oravec, J.A.: Expert systems and knowledge-based engineering (1984–1991). Int. J. Des. Learn. 5(2), 66–75 (2014)

    Google Scholar 

  30. Reed, R., Marks, R.: Neural Smithing: Supervised Learning in Feedforward Artificial Neural Networks. Bradford Book. MIT Press, Cambridge (1999)

    Book  Google Scholar 

  31. Sutton, R.S., Barto, A.G.: Introduction to Reinforcement Learning, 1st edn. MIT Press, Cambridge (1998)

    MATH  Google Scholar 

  32. Towell, G.G., Shavlik, J.W.: Knowledge-based artificial neural networks. Artif. Intell. 70(1–2), 119–165 (1994). https://doi.org/10.1016/0004-3702(94)90105-8

    Article  MATH  Google Scholar 

  33. Tseng, H.H., Luo, Y., Haken, R.T., Naqa, I.E.: The role of machine learning in knowledge-based response-adapted radiotherapy. Front. Oncol. 8, 266 (2018)

    Article  Google Scholar 

  34. Tu, J.V.: Advantages and disadvantages of using artificial neural networks versus logistic regression for predicting medical outcomes. J. Clin. Epidemiol. 49(11), 1225–1231 (1996)

    Article  Google Scholar 

  35. Ulam, P., Goel, A., Jones, J., Murdock, W.: Using model-based reflection to guide reinforcement learning. In: Fourth AAAI Conference on AI in Interactive Digital Entertainment (2008)

    Google Scholar 

  36. Voss, V., Nechepurenko, L.: FreeCiv Games Played by Knowledge-based Reinforcement Learning (2019). https://doi.org/10.5281/zenodo.3266624

  37. Voss, V., Nechepurenko, L., Schaefer, R., Bauer, S.: Playing a strategy game with knowledge-based reinforcement learning. SN Comput. Sci. 1(2), 78 (2020)

    Article  Google Scholar 

  38. Watson, I., Azhar, D., Chuyang, Y.T., Pan, W., Chen, G.: Optimization in Strategy Games : Using Genetic Algorithms to Optimize City Development in FreeCiv (2009). https://doi.org/10.1.1.567.7035

  39. Wender, S.: Integrating Reinforcement Learning into Strategy Games. Master’s thesis, The University of Auckland, Auckland, New Zealand (2009)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Arago GmbH, Eschersheimer Landstr. 526-532, 60433, Frankfurt am Main, Germany

    Liudmyla Nechepurenko, Viktor Voss & Vyacheslav Gritsenko

Authors
  1. Liudmyla Nechepurenko
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Viktor Voss
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Vyacheslav Gritsenko
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Liudmyla Nechepurenko .

Editor information

Editors and Affiliations

  1. University of Oviedo, Oviedo, Spain

    Enrique Antonio de la Cal

  2. University of Oviedo, Oviedo, Spain

    José Ramón Villar Flecha

  3. University of A Coruña, Ferrol, Spain

    Héctor Quintián

  4. University of Salamanca, Salamanca, Spain

    Emilio Corchado

Rights and permissions

Reprints and permissions

Copyright information

© 2020 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Nechepurenko, L., Voss, V., Gritsenko, V. (2020). Comparing Knowledge-Based Reinforcement Learning to Neural Networks in a Strategy Game. In: de la Cal, E.A., Villar Flecha, J.R., Quintián, H., Corchado, E. (eds) Hybrid Artificial Intelligent Systems. HAIS 2020. Lecture Notes in Computer Science(), vol 12344. Springer, Cham. https://doi.org/10.1007/978-3-030-61705-9_26

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-61705-9_26

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-61704-2

  • Online ISBN: 978-3-030-61705-9

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics