Procedural Content Generation for GDL Descriptions of Simplified\n Boardgames

We present initial research towards procedural generation of Simplified\nBoardgames and translating them into an efficient GDL code. This is a step\ntowards establishing Simplified Boardgames as a comparison class for General\nGame Playing agents. To generate playable, human readable, and balanced\nchess-like games we use an adaptive evolutionary algorithm with the fitness\nfunction based on simulated playouts. In future, we plan to use the proposed\nmethod to diversify and extend the set of GGP tournament games by those with\nfully automatically generated rules.\n