Đang chuẩn bị nút TẢI XUỐNG, xin hãy chờ
Tải xuống
Outline: Agents and environments, PEAS (Performance measure, Environment, Actuators, Sensors), Environment types, Agent types. An agent is anything that can be viewed as perceiving its environment through sensors and acting upon that environment through actuators. | Artificial Intelligence For HEDSPI Project Lecture 2 - Agent Lecturers Dr. Le Thanh Huong Dr. Tran Due Khanh Dr. Hai V. Pham School of Information and Communication Technology -HUST Outline Agents and environments PEAS Performance measure Environment Actuators Sensors Environment types 4. Agent types 1 Agents and environments An agent is anything that can be viewed as perceiving its environment through sensors and acting upon that environment through actuators Example 1 human agent Sensors eyes ears . Actuators hands legs mouth . Example 2 robotic agent e.g. Aishimo Sensors camera infrared range finders Actuators various motors Agents and environments con t The agent function maps from percept histories to actions f p JT The agent program runs on the physical architecture to produce the agent function agent architecture program 2 Agent function based on conditional table Function TABLE-DRIVEN-AGENT percept returns an action static percepts a sequence initially empty table a table of actions indexed by percept sequences initially fully specified Append percept to the end of percepts action - LOOKUP percepts table Return action Drawback huge table Vacuum-cleaner world A B Percepts location A or B state clean or dirty Actions Left Right Suck NoOp Percept sequence Action A clean A dirty B clean B dirty A clean A clean A clean A dirty Right Suck Left Suck Right Suck
