Skip to main content
SpringerLink
Log in

Neural Learning of Heuristic Functions for General Game Playing

  • Conference paper
  • First Online:
Machine Learning, Optimization, and Big Data (MOD 2016)

Part of the book series: Lecture Notes in Computer Science ((LNISA,volume 10122))

Included in the following conference series:

Abstract

The proposed model represents an original approach to general game playing, and aims at creating a player able to develop a strategy using as few requirements as possible, in order to achieve the maximum generality. The main idea is to modify the known minimax search algorithm removing its task-specific component, namely the heuristic function: this is replaced by a neural network trained to evaluate the game states using results from previous simulated matches. A method for simulating matches and extracting training examples from them is also proposed, completing the automatic procedure for the setup and improvement of the model. Part of the algorithm for extracting training examples is the Backward Iterative Deepening Search, a new original search algorithm which aims at finding, in a limited time, a high number of leaves along with their common ancestors.

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

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • 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

Notes

  1. 1.

    In the case of the proposed system, since the output is real-valued, the equality constraint must be softened and all values within a margin \(\varepsilon \) are accepted.

  2. 2.

    The complete tree of a game is the tree having as root the initial state and as children of a node all the states reachable with a single legal move from that node. The leaves of this tree are the terminal states of the game.

  3. 3.

    The most common commercial versions of this game are played on a suspended grid, where tokens fall until the lowest free position.

  4. 4.

    The branching factor is the average number of branches (successors) from a (typical) node in a tree. It indicates the bushiness and hence the complexity of a tree. If a tree branching factor is B, then at depth d there will be approximately \(B^d\) nodes.

References

  1. Silver, D., Huang, A., et al.: Mastering the game of Go with deep neural networks and tree search. Nature 529(7587), 484–489 (2016)

    Article  Google Scholar 

  2. Draper, S., Rose, A.: Sancho GGP player. http://sanchoggp.blogspot.com

  3. Michulke, D.: Neural networks for high-resolution state evaluation in general game playing. In: IJCAI-11 Workshop on General Game Playing (GIGA11), pp. 31–37 (2011)

    Google Scholar 

  4. Schiffel, S., Thielscher, M.: Fluxplayer: a successful general game player. In: 22nd National Conference on Artificial intelligence, pp. 1191–1196. AAAI Press, Menlo Park (2007)

    Google Scholar 

  5. Świechowski, M., Mańdziuk, J.: Specialized vs. multi-game approaches to AI in games. In: Angelov, P., et al. (eds.) Intelligent Systems 2014. AISC, vol. 322, pp. 243–254. Springer, Heidelberg (2015). doi:10.1007/978-3-319-11313-5_23

    Google Scholar 

  6. Świechowski, M., Park, H., Mańdziuk, J., Kim, K.-J.: Recent advances in general game playing. Sci. World J. 2015, Article ID 986262, 22 p. (2015). doi:10.1155/2015/986262

    Google Scholar 

  7. Schmidt, W.F., Kraaijveld, M., Duin, R.P.W., et al.: Feedforward neural networks with random weights. In: International Conference on Pattern Recognition, Conference B: Pattern Recognition Methodology and Systems, pp. 1–4 (1992)

    Google Scholar 

  8. Pao, Y.H., Park, G.H., Sobajic, D.J.: Learning and generalization characteristics of the random vector functional-link net. Neurocomputing 6, 163–180 (1994)

    Article  Google Scholar 

  9. Huang, G.B., Chen, L., Siew, C.K.: Universal approximation using incremental constructive feedforward networks with random hidden nodes. IEEE Trans. Neural Netw. 17, 879–892 (2006)

    Article  Google Scholar 

  10. Liang, N.Y., Huang, G.B., Saratchandran, P., Sundararajan, N.: A fast and accurate online sequential learning algorithm for feedforward networks. IEEE Trans. Neural Netw. 17, 1411–1423 (2006)

    Article  Google Scholar 

  11. Russell, S., Norvig, P.: Artificial Intelligence: A Modern Approach. Prentice-Hall, Egnlewood Cliffs (1995)

    MATH  Google Scholar 

  12. Penrose, R.: On best approximate solutions of linear matrix equations. Math. Proc. Camb. Philos. Soc. 52, 17–19 (1956)

    Article  MathSciNet  MATH  Google Scholar 

  13. Bishop, C.: Pattern Recognition and Machine Learning. Springer, Heidelberg (2006)

    MATH  Google Scholar 

  14. Gherrity, M.: A game-learning machine. Ph.D. thesis, University of California, San Diego (1993)

    Google Scholar 

  15. Allis, L.W.: A knowledge-based approach of connect-four. Technical report, Vrije Universiteit, Subfaculteit Wiskunde en Informatica (1988)

    Google Scholar 

  16. British Othello Federation: Game Rules. http://www.britishothello.org.uk/rules.html

  17. Cirasella, J., Kopec, D.: The History of Computer Games. CUNY Academic Works, New York (2006)

    Google Scholar 

  18. Mitchell, D.H.: Using features to evaluate positions in experts’ and novices’ Othello games. Masters thesis, Northwestern University, Evanston (1984)

    Google Scholar 

  19. MacGuire, S.: Strategy Guide for Reversi and Reversed Reversi. www.samsoft.org.uk/reversi/strategy.htm#position

  20. Mnih, V., Kavukcuoglu, K., Silver, D., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529–533 (2015)

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Computer Science, University of Turin, v. Pessinetto 12, 10149, Torino, Italy

    Leo Ghignone & Rossella Cancelliere

Authors
  1. Leo Ghignone
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Rossella Cancelliere
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Rossella Cancelliere .

Editor information

Editors and Affiliations

  1. Department of Industrial and Systems Engineering, University of Florida, Gainesville, Florida, USA

    Panos M. Pardalos

  2. Semantic Technology Laboratory, National Research Council (CNR), Catania, Italy

    Piero Conca

  3. Dipartimento di Sociologia e Metodi della Ricerca Sociale, Università di Catania, Catania, Italy

    Giovanni Giuffrida

  4. Department of Mathematics and Computer Science, University of Catania, Catania, Italy

    Giuseppe Nicosia

Rights and permissions

Reprints and permissions

Copyright information

© 2016 Springer International Publishing AG

About this paper

Cite this paper

Ghignone, L., Cancelliere, R. (2016). Neural Learning of Heuristic Functions for General Game Playing. In: Pardalos, P., Conca, P., Giuffrida, G., Nicosia, G. (eds) Machine Learning, Optimization, and Big Data. MOD 2016. Lecture Notes in Computer Science(), vol 10122. Springer, Cham. https://doi.org/10.1007/978-3-319-51469-7_7

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-51469-7_7

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-51468-0

  • Online ISBN: 978-3-319-51469-7

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation