Details
Reinforcement learning (RL) is a computation approach to learning whereby an agent tries to maximize the total amount of reward it receives when interacting with a complex, uncertain environment. This lecture will introduce the basic theory of reinforcement learning and its applications to the design of human-level artificial intelligence.
Outline:
- Introduction to reinforcement learning and its framework
- RL solutions: model-based methods
- RL solutions: model-free methods
- Deep reinforcement learning
- Real-world applications: Alpha Go, Self-driving cars, Robotics, finance, etc.
About the speaker:
Chong Li, Ph.D. (https://www.linkedin.com/in/chongli727/).
Dr. Li is an expert in the field of AI and blockchain technology. He is a co-founder of NTLabs, a blockchain, and AI-focused research lab, and also an adjunct professor at Columbia University, teaching graduate-level courses such as blockchain, reinforcement learning, and convex optimization. Dr. Li holds more than 200 patents. He’s also the author of the book “Reinforcement Learning for Cyber-physical Systems” (Taylor & Francis CRC press).
In addition to publishing papers on top-ranking academic journals, including Proceedings of the IEEE, IEEE Transactions on Information Theory, IEEE Communications Magazine, Automatica, etc., he serves as a reviewer and technical program committee for most prestigious journals and conferences in communications and control societies as well. Dr. Li is a grant reviewer for the Natural Sciences and Engineering Research Council of Canada. He is an IEEE senior member.