The course description: Introduction to Augmented Learning, Machine Learning, Intelligent Agent, and Multi-Agent System, and the continuous interaction of agents with their surrounding environments. The relationship between Augmented Learning and Machine Learning, the scope of supervised and unsupervised learning, the actions of the agent, and its interactive behavior in the environment. Research achievements of Augmented Learning in theoretical and applied fields, its applications in robotics, pattern recognition, personalized medical treatments, drug discovery, speech recognition, computer vision, and natural language processing. The framework of Augmented Learning and its challenges, and its basic algorithms. A review of the modern methods derived from it such as imitation learning and meta learning, and the design of complex interactive environments.
Credit hours: 3
Objectives of the course :
– Learn how to formulate and identify augmented learning tasks and key principles such as policies, value functions, and deriving Bellman Equations.
– Programming and application of common algorithms in programming code according to approved standards and using specialized libraries for augmented learning.
– Incorporating and applying tabular methods to address traditional control and adjustment problems.
– Incorporating and applying approximation solutions based on deep Q-network algorithms.
– Mastery of Policy Gradient Methods starting from basic cases and reaching complex models.
– Exploring and absorbing the tasks and solutions of simulation and imitation learning.
– Understanding the latest advanced technologies and contemporary applications in augmented learning.
Course outputs :
1.1 Incorporating the essential advantages and characteristics of reinforcement learning that distinguish it from non-interactive artificial intelligence and machine learning.
1.2 Accommodating the multiple standards used to analyze and compare reinforcement learning algorithms.
2.1 Effective application of the most popular reinforcement learning algorithms.
2.2 Making the correct predictive decision about whether an application problem is suitable to be formulated as an augmentative learning problem.
3.1 Cooperative and positive collaboration with the work team within the completion of the specialized project.
This website uses special cookies to ensure ease of use, improve your browsing experience, and clarify the terms and policies related to About user privacy. By continuing to browse this website, you acknowledge that you accept the use of cookies and the terms of the Privacy Policy