Learning situational knowledge through observation of expert performance in a simulation-based environment

Most knowledge acquisition techniques are best suited for gathering knowledge in a static domain; they are incapable of handling dynamically changing information as is frequently encountered in a real time simulation. This research describes a general methodology for learning implicit situational knowledge by observing the expert while reacting to a real time simulation. The paper outlines an efficient methodology to gather, represent, and learn expert knowledge by examining the expert's simulated surroundings while simultaneously monitoring the expert's actions for a given situation. It utilizes recent advances in the areas of neural networks and artificial intelligence to establish a suitable knowledge representation schema that incorporates both numeric and symbolic forms of knowledge. The method demonstrates the ability to train on basic skills and to generalize learned actions to handle more complex situations not previously encountered.