人工智能02智能体.pptxVIP

第二章 智能体教材 Artificial Intelligence – A modern approach (2013)S. Russell and P. Norvig人工智能—一种现代方法(第二版)学校发的教材参考概率推理、机器学习部分理性的行动：Maximize Your?Expected Utility使目标期望值最大化！智能体An agent is anything that can be viewed as perceivingits environment through sensorsand acting upon that environment through actuators。 一个智能体是能通过传感器来感知周围环境并通过执行器来行动的任何东西。Agents include humans, robots, softbots（软件机器人） ,thermostats（自动调温器） , etc.Human agent人类智能体: eyes, ears, and other organs for sensors; hands, legs, mouth, and other body parts for actuatorsRobotic agent机器人智能体: cameras and infrared range finders（红外测距仪） for sensors; various motors(马达) for actuators智能体和环境The agent function（智能体函数） maps from percept histories（感知序列） to actions（行动）: [f: P*→ A]The agent program（智能体程序） runs on the physical architecture toproduce fagent = architecture（体系结构） + program（程序）两地点真空吸尘器世界Percepts: location and contents, e.g., [A,Dirty]Actions: Left, Right, Suck, NoOp真空吸尘智能体What is the right function?Can it be implemented（应用） in a small agent program?理性智能体An agent should strive to “do the right thing”, based on what itcan perceive and the actions it can perform. The right action isthe one that will cause the agent to be most successful对的行动就是使智能体更加成功的行动Performance measure（性能度量） : An objective criterion（客观标准） for success of an agents behaviorE.g., performance measure of a vacuum-cleaner agent couldbe： 灰尘清理量 耗电量 噪音产生量, etc.理性智能体Rational Agent: For each possible percept sequence, arational agent should select an action that is expectedto maximize its performance measure, given theevidence provided by the percept sequence andwhatever built-in knowledge the agent has.理性智能体： 对于每一个可能的感知序列，理性智能体应该基于已知的感知序列提供的信息，和智能体已有的先验知识，选择能够使它的性能度量最大化的行为。理性智能体理性与全知 (all-knowing with infinite knowledge)是截然不同的Agents can perform actions in order to modify futurepercepts so as to obtain useful information(information gathering, exploration) 智能体会为了获取有用信息而采取行动——信息收集An agent is autonomous if its behavior is determinedby its own experience (with abili