Reinforcement learning refers to a class of techniques that combine aspects of optimal control, simulation/data driven optimization, and approximation methods for problems of dynamic decision making under uncertainty when the model of the underlying system and its processes is unknown. A large portion of the algorithms and techniques used here are model-free in nature and as a result need no knowledge of the system dynamics and protocols used. Reinforcement Learning thus finds applications in several diverse areas such as Adaptive Control, Signal Processing, Manufacturing, Communication and Wireless Networks, Autonomous Systems and Data Mining. The objective of this course will be to provide a strong foundation in Reinforcement Learning through the various tools, techniques and algorithms used as well as to cover the state-of-the-art algorithms in Deep Reinforcement Learning involving simulation-based neural network methods.

Introduction to Reinforcement Learning, Multi-armed bandits, Markov decision processes, Dynamic Programming Value and Policy Iteration Methods, Model-Free Learning Approaches, Monte-Carlo Methods, Temporal Difference Learning, Q-learning, SARSA, Double Q-learning, Value Function Approximation Methods TD Learning with Linear Function Approximation, Neural Network Architectures, Deep Q-Network Algorithm, Policy Gradient Methods, ActorCritic Algorithms.

B.Tech (any discipline); B.Sc in Mathematics / Statistics /Computer Science / Physics / Data Science.

1. R.Sutton and A.Barto, Reinforcement Learning, 2018 (MIT Press)
2. Recent papers (to be shared in class)