Reinforcement Learning Programming (AIDI 1008)
Reinforcement learning utilizes software agents to make decisions in a simulated environment and use a reward/penalty system for achieving goals or making mistakes. Through numerous iterations of the simulation the algorithms learn and adjust in order to provide the best possible outcome. Students learn how to leverage reinforcement learning concepts such as dynamic programming, Q-learning, State-Action-Reward-State-Action (SARSA) and Deep Deterministic Policy Gradient (DDPG) to solve artificial intelligence problems that are highly dimensional.
Credits:
Credit Hours | Contact Hours | Lecture Hours | Lab Hours | Other |
---|---|---|---|---|
3.000 |
42.000 |
|
|
|
[+] Prerequisites:
[+] Corequisites and Concurrent Prerequisite(s):
None
[+] Equivalents:
[-] Restrictions:
Must be enrolled in one of the following Levels:
Post Graduate
Must be enrolled in one of the following Majors:
(AIDI) Artificial Intelligence