Design and Evaluation of Reinforcement Learning Based AI Agent: A Case Study in Gaming

Soft computing is extensively used in the field of computer games to create AI agents for computers. A case study of reinforcement learning is presented, by designing an AI agent for chopsticks game, with a probabilistic algorithm devised to make use of past game experience as its only tool to guide itself to victory. It has been experimentally verified that the AI agent’s performance increases with learning and nears saturation beyond a point of learning. Constant order space and time complexity is achieved with proper design of knowledge base.

[1]  Wolfgang Konen,et al.  Reinforcement Learning with N-tuples on the Game Connect-4 , 2012, PPSN.

[2]  Ralph Gasser,et al.  SOLVING NINE MEN'S MORRIS , 1996, Comput. Intell..

[3]  Richard S. Sutton,et al.  Introduction to Reinforcement Learning , 1998 .

[4]  Eduardo M. Morales,et al.  LEARNING PLAYING STRATEGIES IN CHESS , 1996, Comput. Intell..

[5]  Andrew W. Moore,et al.  Reinforcement Learning: A Survey , 1996, J. Artif. Intell. Res..

[6]  H. Jaap van den Herik,et al.  Proof-Number Search , 1994, Artif. Intell..

[7]  Krzysztof Krawiec,et al.  Learning n-tuple networks for othello by coevolutionary gradient search , 2011, GECCO '11.

[8]  H. Jaap van den Herik,et al.  GO‐MOKU SOLVED BY NEW SEARCH TECHNIQUES , 1996, Comput. Intell..

[9]  Wolfgang Konen,et al.  Temporal difference learning with eligibility traces for the game connect four , 2014, 2014 IEEE Conference on Computational Intelligence and Games.

[10]  Lin Wu,et al.  A Scalable Machine Learning Approach to Go , 2006, NIPS.

[11]  Harsh Bhasin,et al.  Genetic based Algorithm for N - Puzzle Problem , 2012 .

[12]  Stefan Wrobel,et al.  Learning Minesweeper with Multirelational Learning , 2003, IJCAI.

[13]  Christopher J. Gatti,et al.  Reinforcement learning and the effects of parameter settings in the game of Chung Toi , 2011, 2011 IEEE International Conference on Systems, Man, and Cybernetics.

[14]  Gerald Tesauro,et al.  Temporal difference learning and TD-Gammon , 1995, CACM.

[15]  Graham Kendall,et al.  A Survey of NP-Complete Puzzles , 2008, J. Int. Comput. Games Assoc..

[16]  Abhijit Gosavi,et al.  Reinforcement Learning: A Tutorial Survey and Recent Advances , 2009, INFORMS J. Comput..