Game Playing Agent Using Artificial Neural Network

Authors

  • Deepti Rai  Sr. Assistant Professor, Department of Computer Science and Engineering, New Horizon College of Engineering, Bangalore, Karnataka, India

Keywords:

Machine Learning, Artificial Neural Network (ANN), Reinforcement Learning, Q-Learning

Abstract

The project focuses to train a game playing agent to learn the game. AI comprises of the neural systems ANN where the neural system produces the controls for playing the game. Based on the Reinforcement Learning technique selections are done subjecting on the information which is collected from the environment. Here, Q-Learning is used where the agent decides the actions based on conditions. Here, the interface Unity SDK is used to build the game.

References

  1. Matthew S. Emigh , Evan G. Kriminger, Austin J. Brockmeier, Jose C. Principe and Panos M. Pardalos, “Reinforcement Learning in Video Games using Nearest Neighbor Interpolation and Metric Learning”, IEEE Transactions on Computational Intelligence and AI in Games, ISSN(e):1943-0698, Vol-08, Issue-01, March-2016, pp.56-
  2. Sebastian Risi and Julian Togelius, “Neuroevolution in Games: State of the Art and Open Challenges”, IEEE Transactions on Computational Intelligence and AI in Games, ISSN(e):1943-0698, Vol-09, Issue-01, March-2017, pp.25-41
  3. Daniel Jallov, Sebastian Risi and Julian Togelius, “EvoCommander: A Novel Game Based on Evolving and Switching Between Artificial Brains”, IEEE Transactions on Computational Intelligence and AI in Games, ISSN(e):1943-0698, Vol-09, Issue-02, June-2017, pp.181-191
  4. Sam Snodgrass and Santiago Ontanon, “Learning to Generate Video Game Maps Using Markov Models”, IEEE Transactions on Computational Intelligence and AI in Games, ISSN(e):1943-0698, Vol-09, Issue-04, December-2017, pp.410-422
  5. Pawel Liskowski, Wojciech Jaskowski, Krzysztof Krawiec, ”Learning to Play Othello with Deep Neural Networks”, IEEE Transactions on Games, ISSN(e):2475-1510,pp.1-1.
  6. Peizhi Shi and Ke Chen, “Learning Constructive Primitives for Real-Time Dynamic Difficulty Adjustment in Super Mario Bros”, IEEE Transactions on Games,ISSN(e):2475-1510, Vol-10, Issue-02, June-2018, pp.155-169.
  7. Tristan Cazenave, “Residual Networks for Computer Go”, IEEE Transactions on Games, ISSN(e):2475-1510, Vol-10, Issue-01, March-2018, pp.107-110
  8. Xiaomin Lin, Peter A. Beling and Randy Cogill, “Multiagent Inverse Reinforcement Learning for Two-Person Zero-Sum Games”, IEEE Transactions on Games,ISSN(e):2475-1510, Vol-10, Issue-01, March-2018, pp.56-68.
  9. Hendrik Baier, Adam Sattaur, Edward J. Powley, Sam Devlin, Jeff Rollason and Peter I. Cowling, “Emulating Human Play in a Leading Mobile Card Game”, IEEE Transactions on Games, ISSN(e):2475-1510, pp.1-1
  10. Hao Wang, Hao-Tsung and Cheun-Tsai Sun, ”Thinking Style and Team Competition Game Performance and Enjoyment”, IEEE Transactions on Computational Intelligence and AI in Games, ISSN(e):1943-0698, Vol-07, Issue-03, September-2015,pp.243-254.
  11. Federico Chesani, Andrea Galassi, Marco Lippi and Paola Mello, “Can Deep Networks Learn to Play by the Rules? A Case Study on Nine Men’s Morris”, IEEE Transactions on Games, ISSN(e):2475-1510, pp.1-1.

IInternational Journal of Scientific Research in Computer Science, Engineering and Information Technology

Downloads

Published

2019-12-30

Issue

Volume 4, Issue 9, November-December-2019

Section

Research Articles

License

Copyright (c) IJSRCSEIT

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

How to Cite

[1]
Deepti Rai, " Game Playing Agent Using Artificial Neural Network" International Journal of Scientific Research in Computer Science, Engineering and Information Technology(IJSRCSEIT), ISSN : 2456-3307, Volume 4, Issue 9, pp.442-445, November-December-2019.