אוניברסיטת בן - גוריון בנגב הפקולטה למדעי הטבע - המחלקה למדעי המחשב סמסטר א ' תש פ" ה סילבוס קורס שם קורס: בינה מלאכותית: תכנון וקבלת החלטות שם קורס באנגלית: Artificial Intelligence Planning and Decision Making מספר קורס: 202 - 2 - 5171 סוג קורס: בחירה נק"ז: 4.0 מרצה הקורס: פרופ' רונן ברפמן דרישות קדם: 202 - 1 - 2041 תכנון אלגוריתמים 201 - 1 - 3011 מבוא ל הסתברות למדמ"ח סילבוס באנגלית: The goal of this course is to gain familiarity with models and algorithms developed, mostly in the field of Artificial Intelligence, for automating the process of decision making and planning with major emphasis on Reinforcement Learning and roboti applications The two main motivations are to help build autonomous systems, such as the rovers NA SA landed on Mars and other robots, or artific ial characters in a computer game, as well as provide technology for decision - support systems. Given a model of a system, such as a robot on Mars, we could write a program that tells it how to behave, but we would prefer to simply tell it what we want to a ccomplish and have it automatically decide what actions to take. In many cases, a model is either too complex to explicitly provide, or is simply unknown to us. In such cases, we would like the system to gradually improve its behavior by learning based on feedbacks it receives from the environment. The course will consider both cases and will cover topics such as: reinforcement learning and deep reinforcement learning, classical planning and classical אוניברסיטת בן - גוריון בנגב הפקולטה למדעי הטבע - המחלקה למדעי המחשב סמסטר א ' תש פ" ה planning algorithms , Markov decision processes and parti ally observable Markov decision processes, multi - agent planning, motion planning algorithms, and methods for generating heuristic functions. Additional advanced topic may be added, such as imitation learning. The workload is as follows: 1. Some self - learning using online resources 2. Online review quizzes 3. P rogramming assignments with a focus on RL 4. W ritten assignments focusing on planning models 5. Final exam Course grade: Final exam 50% Assignments 40% Attendance and online quizzes 10% Depending on circumstances, the attendance component may be optional.