The Course Will Be Dedicated to Understanding The Science Of Single-agent Sequential Decision-making in Ai. The Focus Will Be On Promoting Efficient Behaviors of Agents That Need to Accomplish Complex Tasks in Uncertain Environments Even When The Environment Dynamics Are Not Fully Known. The Course Will Start By Covering The Main Common Ai Approaches To Sequential Decision-making Under Uncertainty For a Single Agent. This Includes Both Planning, For Settings in Which The Agent Has A Complete Model of The Underlying Environment, and Reinforcement Learning (rl), For Settings in Which The Model of The Environment Is Only Partially Known. The Course Will Include Learning The Theoretical Aspects of Various Ai Frameworks, As Well As Practical Work With Different Systems, Using Python Based Implementations. Students Will Be Required to Run Various Planning, Rl, and Deep-rl Algorithms On Different Domains And Analyze The Performance of The Different Approaches. Learning Outcomes# at The End of The Course The Students Will Be Able To Know# 1. Knowledge of Various Ai Frameworks For Modeling Single-agent Ai Settings. 2. Understanding The Theoretical Guarantees and Limitations Of Different Ai Algorithms For Single-agent Planning and Rl. 3. Acquiring Practical Experience Using Ai Tools and Implementing Them In Various Ai Domains. 4. Experience in Analyzing The Performance of Different Ai Approaches.

Faculty: Computer Science
|Undergraduate Studies |Graduate Studies
Pre-required courses

236501 - Introduction to Artificial Intelligence

Course with no extra credit (contains)

236203 - Advanced Topics in Collabortive Artifici