On verifying game designs and playing strategies using reinforcement learning
Dimitris Kalles, Panagiotis N. Kanellopoulos · 2001
In this paper we elaborate on the application of reinforcement learning to the details of the design and the verification of a new strategy game. We deal with playability and learning issues, using a "raw state" representation. The machine's a priori knowledge about the game is restricted to the rules only. Keywords: Reinforcement learning, machine learning, games, playability, design verification. 1.