Predatory Sequence Learning for Synthetic Characters
Matt Berlin · DSpace@MIT (Massachusetts Institute of Technology) · 2003
The process of mammalian predatory sequence development offers a number of insights rele-vant to the goal of designing synthetic characters that can quickly and easily learn complicated and interesting behavior. We propose a number of principles for designing such learning sys-tems, inspired by a targeted review of animal developmental phenomena, with particular emphasis on the development of predatory behavior in certain felid and canid species. We describe the implementation of a few of these principles as an extension to a popular algo-rithm for learning in autonomous systems called hierarchical Q-learning. In this new approach, the agent starts out with only one skill, and then new skills are added one at a time to its available repertoire as time passes. The agent is motivated to experiment thoroughly with each new skill as it is introduced. Simulation results are presented which empirically demon-strate the advantages of this new algorithm for the speed and effectiveness of the learning pro-