Evaluating the effectiveness of exploration and accumulated experience in automatic case elicitation
ICCBR'05 Proceedings of the 6th international conference on Case-Based Reasoning Research and Development
Towards using first-person shooter computer games as an artificial intelligence testbed
KES'05 Proceedings of the 9th international conference on Knowledge-Based Intelligent Information and Engineering Systems - Volume Part I
| Hi-index | 0.00 |
MAYOR is a real-time player of the popular simulation game SimCity. Since SimCity is a complex, dynamic world, players must make do with a partial understanding of how the world works. MAYOR contends with an incomplete world model by using a case-based planner which repairs plans on expectation failures, and with experience can improve its case library. SimCity players must also be able to quickly prioritize many tasks, which range from short to long-term. MAYOR uses utility estimates based on historical observation of the success of past tasks. This paper describes these approaches, and provides an overview of the MAYOR architecture.