Csaba Szepesvari, PhD

Area of Study / Keywords

Learning theory machine learning reinforcement learning online learning bandits

About

Education

• M.Sc., Mathematics, Jozsef Attila University, 1993
• M.Sc., Computer Science, Jozsef Attila University, 1993
• Ph.D., Probability and Statistics, Jozsef Attila University, 1999

Research

Areas

Artificial Intelligence

Machine Learning

Reinforcement Learning

Summary

Traditional programming fails miserably when computers need to interact with the `real-world'. Examples include a robot whose mission is to explore Mars or to clean up a room, an algorithm that needs to decide if a person should be given credit, or a chat-bot conversing with humans in English. Artificial intelligence is the science whose aim is to create computer programs that are able to cope with problems like these.

A core tool of artificial intelligence is machine learning. Machine learning allows computers to learn from data. This way computers can discover solutions to difficult problems on their own.

My research focuses on creating smart, efficient learning algorithms. I am working on developing better learning algorithms and understanding what makes efficient learning possible. I am particularly interested in problems when a machine continuously interacts with its environment while trying to discover autonomously a good way of interacting with it.

Prospective students should look at my personal homepage.

CMPUT 365 - Introduction to Reinforcement Learning

This course provides an introduction to reinforcement learning, which focuses on the study and design of learning agents that interact with a complex, uncertain world to achieve a goal. The course will cover multi- armed bandits, Markov decision processes, reinforcement learning, planning, and function approximation (online supervised learning). The course will take an information-processing approach to the study of intelligence and briefly touch on perspectives from psychology, neuroscience, and philosophy. The course will use the University of Alberta MOOC on Reinforcement Learning. Any student who understands the material in this course will understand the foundations of much of modern probabilistic artificial intelligence (AI) and be prepared to take more advanced courses, or to apply AI tools and ideas to real-world problems. Prerequisites: CMPUT 175 or 275; one of CMPUT 267, 466, or STAT 265.

CMPUT 605 - Topics in Computing Science

Browse more courses taught by Csaba Szepesvari