Sorry, you need to enable JavaScript to visit this website.

  • 10:45 AM, Tuesday, 04 Aug 2020


Course Postgraduate
Semester Electives
Subject Code MA867
Subject Title Reinforcement Learning

Syllabus

The reinforcement learning problem; tabular & approximate solution methods: dynamic programming, Monto-Carlo Methods, temporal difference learning, eligibility traces; planning and
learning; dimensions of reinforcement learning.

Text Books
References

1. Sutton R. S. and Barto, A. G., Reinforcement Learning: An Introduction, The MIT Press  (2017).
2. Tesauro G., Temporal Difference Learning and TD-Gammon, Communications of the Association for Computing Machinery (1995).