Title :
Evolving a Mario agent using cuckoo search and softmax heuristics
Author_Institution :
Square Enix Res. Center, Square Enix Co., Ltd., Tokyo, Japan
Abstract :
This paper presents a method for evolving an agent which can successfully play a level of Super Mario Brothers as implemented on the MarioAI Benchmark. The Mario search space is extremely large, making finding reasonable solutions intractable for ordinary agents. The recently introduced evolutionary algorithm, cuckoo search is especially well suited toward searching such large spaces when it employs the use of Lévy flights. Unfortunately, these Lévy flights cannot be applied to non numerical problems such as Mario. We present a modification of the algorithm which uses the Lévy distribution to effect appropriate change in a much wider set of problems, including Mario. To further optimize the search of Mario´s problem space, a softmax heuristic is presented to focus on areas with likely solutions.
Keywords :
artificial intelligence; computer games; evolutionary computation; search problems; software agents; statistical distributions; Lévy distribution; Mario agent; Mario search space; MarioAI Benchmark; Super Mario Brothers; cuckoo search; evolutionary algorithm; softmax heuristics; Artificial intelligence; Benchmark testing; Evolutionary computation; Games; Optimization; Radio frequency; Space exploration; Le´vy flights; Super Mario Bros; cuckoo search; evolutionary algorithm; softmax;
Conference_Titel :
Games Innovations Conference (ICE-GIC), 2010 International IEEE Consumer Electronics Society's
Conference_Location :
Hong Kong
Print_ISBN :
978-1-4244-7178-2
Electronic_ISBN :
978-1-4244-7179-9
DOI :
10.1109/ICEGIC.2010.5716893