/enri-thumbnails/careeropportunities1f0caf1c-a12d-479c-be7c-3c04e085c617.tmb-mega-menu.jpg?Culture=en&sfvrsn=d7261e3b_1)
/cradle-thumbnails/research-capabilities1516d0ba63aa44f0b4ee77a8c05263b2.tmb-mega-menu.jpg?Culture=en&sfvrsn=1bc94f8_1)
7e6fdc03-9018-4d08-9a98-8a21acbc37ba.tmb-mega-menu.jpg?Culture=en&sfvrsn=7deaf618_1)
Introduction
This course provides an introduction to some of the foundational ideas on which modern reinforcement learning is built, including Markov decision processes, value functions, Monte Carlo estimation, dynamic programming, temporal difference learning, eligibility traces, and function approximation. This course will develop an intuitive understanding of these concepts (taking the agent’s perspective), while also focusing on the mathematical theory of reinforcement learning. Programming assignments and projects will require implementing and testing complete decision making systems.
- Graduate Certificate in Artificial Intelligence and AI Ethics
- Graduate Certificate in Data Science and Artificial Intelligence
- Graduate Certificate in Artificial Intelligence and AI Plus
- FlexiMasters in Artificial Intelligence and AI Ethics
- FlexiMasters in Data Science and Artificial Intelligence
- FlexiMasters in Artificial Intelligence and AI Plus
Download Learning Pathway e-Guide
At the end of the course, learners are able to:
1. Build a Reinforcement Learning system for sequential decision making;
2. Understand the space of RL algorithms;
3. Understand how to formalize your task as a Reinforcement Learning problem, and how to begin implementing a solution and;
4. Understand how RL fits under the broader umbrella of machine learning, and how it complements deep learning, supervised and unsupervised learning.
1. Overview of reinforcement learning: the agent environment framework,
successes of reinforcement learning
2. Markov decision processes
3. Returns, and value functions
4. Solution methods: dynamic programming
5. Solution methods: Monte Carlo learning
6. Solution methods: Temporal difference learning
7. Value function approximation (function approximation)
8. Frontiers of RL research
For learner who wish to acquire more knowledge in applying AI practices in organizations and, to understand and help societies to solve problems brought about by the impact of AI.
Standard Course Fee: S$1,962
SSG Funding Support | Course fee | Course fee payable after SSG funding, if eligible under various schemes | |
BEFORE funding & GST | AFTER funding & 9% GST | ||
Singapore Citizens (SCs) and Permanent Residents (PRs) (Up to 70% funding) | S$1,800 | S$588.60 | |
Enhanced Training Support for SMEs (ETSS) | S$228.60 | ||
SCs aged ≥ 40 years old | |||
- Standard course fee is inclusive of GST.
- NTU/NIE alumni may utilise their $1,600 Alumni Course Credits. Click here for more information.
Artificial Intelligence and AI Ethics
| COURSE TITLE | ACADEMIC UNIT |
| CET787 Foundations of Computation Thinking and Programming | 1 |
| CET788 AI 1:AI Foundation | 1 |
| CET790 AI 3: Computational Game Theory | 1 |
| CET791 ML1: Supervised learning: Bayesian decision theory and classifiers | 1 |
| CET792 ML2: Supervised learning: Non-probabilistic classifiers | 1 |
| CET793 ML3: Unsupervised learning | 1 |
| CET794 AI Ethics 1: Foundations of AI Ethics | 1 |
| CET795 AI Ethics 2: AI Ethic Standardization | 1 |
| CET807 Application 2: Introduction to Computer Vision | 1 |
| CET797 Body of Knowledge (BoK) for AI Ethics and Governance | 1 |
| CET798 AI Ethics Governance Framework for Organisations | 1 |
| CET799 Business Liability and Ethics in AI Usage | 1 |
| CET800 AI Ethics 3: Ethics in Data Processing | 1 |
| CET801 Governance for AI Explainability | 1 |
Data Science and Artificial Intelligence
| COURSE TITLE | ACADEMIC UNIT |
| CET787 Foundations of Computation Thinking and Programming | 1 |
| CET788 AI 1:AI Foundation | 1 |
| CET790 AI 3: Computational Game Theory | 1 |
| CET791 ML1: Supervised learning: Bayesian decision theory and classifiers | 1 |
| CET792 ML2: Supervised learning: Non-probabilistic classifiers | 1 |
| CET793 ML3: Unsupervised learning | 1 |
| CET794 AI Ethics 1: Foundations of AI Ethics | 1 |
| CET795 AI Ethics 2: AI Ethic Standardization | 1 |
| CET802 DS1: Descriptive Analytics | 1 |
| CET803 DS2: Predictive Analytics | 1 |
| CET804 DS3: Pattern Recognition | 1 |
| CET805 AI Ethics 3: Ethics in Data Processing | 1 |
| CET806 Application 1: Introduction to Affective AI | 1 |
| CET807 Application 2: Introduction to Computer Vision | 1 |
| CET808 Application 3: Introduction to Cloud AI | 1 |
Listed courses are:
- Credit-bearing and stackable to Graduate Certificate in Artificial Intelligence and AI Ethics, Graduate Certificate in Data Science and Artificial Intelligence (total 9AUs), FlexiMasters in Artificial Intelligence and FlexiMasters in Data Science and Artificial Intelligence (total 15AUs).
- SkillsFuture Credit approved.
