Learning by observation allows a software agent to learn by watching an expert perform a task. This transfers the burden of training from the expert, who would traditionally need to program the agent, to the agent itself. Most existing approaches to learning by observation perform their observation in a purely passive manner. We propose a case-based reasoning agent that is able to observe passively but can also use mixed-initiative control to request assistance from the expert for difficult input problems. Our agent uses mixed-initiative case acquisition in the game of Tetris. We show that the agent is able to obtain cases it would not have been able to with passive observation alone, is able to improve its performance and places less burden on the expert. Copyright

Additional Metadata
Conference 24th International Florida Artificial Intelligence Research Society, FLAIRS - 24
Citation
Floyd, M.W. (Michael W.), & Esfandiari, B. (2011). Supplemental case acquisition using mixed-initiative control. Presented at the 24th International Florida Artificial Intelligence Research Society, FLAIRS - 24.