How do self-driving cars decide the route? How does Alpha-GO come up with game moves to achieve human-level performance? How do Mars rovers operate autonomously? This Spring, our EECS faculty Sandhya Saisubramanian will be teaching a new course (CS 499) on Introduction to Intelligent Decision Making, where you can learn how to design intelligent, autonomous systems. The course will introduce some of the fundamental concepts in reinforcement learning and planning, and common solution methods to solve them. Credits: 4 * NOTE: CS 499 credits can count towards your degree requirements. Check with your advisor! Course Description: Explores key concepts in intelligent decision-making, including agent representation, sequential decision-making frameworks, automated planning, and reinforcement learning. Automated Planning: deterministic planning, probabilistic planning, informed and uninformed search techniques, and dynamic programming (value iteration and policy iteration). Reinforcement learning: Q learning, SARSA, policy gradient methods. Prerequisites: CS 325 or CS 325H, familiarity with a programming language Learning Objectives: By the end of the course, you will be able to: (1) identify which problems can be solved using planning or reinforcement learning; (2) formulate problems using sequential decision making frameworks; and (3) implement some of the popular solution methods to solve these problems. For more information see attached flyer. EECS Advising Team School of Electrical Engineering & Computer Science Oregon State University | 1148 Kelley Engineering Center Schedule Advising Appointment or Attend Drop-ins here<https://eecs.oregonstate.edu/current-students/undergraduate/advising/make-appointment>