Till Miemietz, Christoph Starke, and Lukas Schweizer submitted their AI agent to this years AI Birds Challenge at the International Joint Conference on Artificial Intelligence,(IJCAI), held in Macao. The task of this competition is to develop a computer program that can successfully play Angry Birds. The long term goal is to build an intelligent Angry Birds playing agent that can play new levels better than the best human players. This is a very difficult problem as it requires agents to predict the outcome of physical actions without having complete knowledge of the world, and then to select a good action out of infinitely many possible actions. This is an essential capability of future AI systems that interact with the physical world.
Their agent SimbaDD managed to play quite competitively in this years AI Birds challenge. It uses a simulation based aproach, thus the agent is able to simulate actions in its own physical world. Whereas this is was only the first milestone reached for this years competition, it opens a nice starting point for more features such as learning and planning.
After clearly winning the quarter final, and being placed 2nd with quite some distance to 3rd place in the semi final. Only in the final, we lost some points against the team of Bamberg University.