Reinforcement learning deals with how an agent decides on actions to take in an environment, while intending to maximise some notion of a reward. This course will cover the basic theory of reinforcement learning, based on Markov decision processes and dynamical programming, as well as basic learning methods, such as temporal differences. Two practicals will be included to apply these concepts and methods to specific applications.
Schedule :
Lecture 1: 01 November 2024, 02:00 PM to 04:00 PM
Lecture 2: 05 November 2024, 03:30 PM to 05:00 PM
This course will be conducted in hybrid mode. More details will be shared separately with the registered candidates.
The course will be accessible to anyone (MSc, PhD, or higher) with some knowledge of probability at the undergraduate level. The course will start with a recap on Markov chains and no prior knowledge will be assumed. If you are interested in attending this mini-course, please register by 25th October 2024.
For any queries contact us at : academicoffice@icts.res.in
