人工智能英文版课件：02 Intelligent Agents.pptVIP

* The Structure of Agents Critic Tells the learning element how well the agent is doing with respect to a fixed performance standard It is necessary because the percepts themselves provide no indication of the agent’s success This is important to have a fixed performance measure It is outside the agent Agent must not modify it to fit its own behavior * The Structure of Agents Problem generator Responsible for suggesting actions that will lead to new and informative experiences If the performance element had its way, it would keep doing the actions that are the best given what it knows But, if the agent is willing to explore a little, and do some perhaps suboptimal actions in the short run, it might discover much better actions for the long run It major task is to suggest these exploratory actions Just like human carrying out experiments * The Structure of Agents Galileo, rock and Pisa Galileo did not think that dropping a rock from the top of a tower in Pisa was valuable in itself He was not trying to break the rock He was not trying to “modify” the brains of unfortunate passers-by His aim was to modify his own brain, by identifying a better theory of the motion of objects * The Structure of Agents Example: automated taxi The performance element consists of whatever of knowledge and procedures the taxi has for selecting its driving actions The taxi goes out on the road and drives using this performance element * The Structure of Agents Example: automated taxi The critic observes the world and passes information along to the learning element When the car turns left across 3 lanes, the critic observes shocking language used by other drivers From this experience, the learning element is able to formulate a rule saying that this was a bad action Modify performance element by installing the new rule The problem generator might identify certain areas of behavior in need of improvement and suggest experiments Trying out the brakes on different road surfaces under different