AAAI Publications, Ninth Artificial Intelligence and Interactive Digital Entertainment Conference

Font Size: 
Generating Believable Stories in Large Domains
Bilal Kartal, John Koenig, Stephen J. Guy

Last modified: 2013-11-13


Planning-based techniques are a very powerful tool for automated story generation. However, as the number of possible actions increases, traditional planning techniques suffer from a combinatorial explosion due to large branching factors. In this work, we apply Monte Carlo Tree Search (MCTS) techniques to generate stories in domains with large numbers of possible actions (100+). Our approach employs a Bayesian story evaluation method to guide the planning towards believable stories that reach a user defined goal. We generate stories in a novel domain with different type of story goals. Our approach shows an order of magnitude improvement in performance over traditional search techniques.


Monte Carlo Tree Search, Upper Confidence Bounds, UCB, MCTS, Exploration versus Exploitation

Full Text: PDF