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

This paper outlines an efficient method to gather, represent, and learn expert knowledge by examining the expert\u27s simulated surroundings while simultaneously monitoring the expert\u27s actions for a given situation. It uses recent advances in the areas of neural networks and artificial intelligence to establish a suitable knowledge and 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