Search Algorithm with Learning Ability for Mario AI -- Combination A* Algorithm and Q-Learning
Shunsuke Shinohara, Toshiaki Takano, Haruhiko Takase, Hiroharu Kawanaka, Shinji Tsuruoka · 2012
Computer Games are extremely challenging benchmarks for artificial intelligence in general. They need dynamic path planning in dynamic environments, learning ability and cooperative behaviors. We focus on Mario AI benchmark that evaluates AI controllers which is made by participants. To challenge the benchmark, we discuss the cooperative intelligence. It is difficult that agents obtain an optimal action rule in Mario AI benchmark because of large state space and time limit and so on. In this article, we add learning ability to search algorithm. It would be one kind of cooperative intelligence. We focus on A* algorithm for Search algorithm and Q-learning for learning ability. By some experiments, we show that the proposed method works well in MarioAI.