Reinforcement learning is a paradigm that aims to model the trial-and-error learning process that is needed in many problem situations where explicit instructive signals are not available. It has roots in operations research, behavioral psychology and AI. The goal of the course is to introduce the basic mathematical foundations of reinforcement learning, as well as highlight some of the recent directions of research.
INTENDED AUDIENCE : Any interested learnerINDUSTRY SUPPORT :Data analytics/data science/robotics
COURSE LAYOUT Week 1 : IntroductionWeek 2 : Bandit algorithms – UCB, PACWeek 3: Bandit algorithms –Median Elimination, Policy GradientWeek 4: Full RL & MDPsWeek 5 : Bellman OptimalityWeek 6: Dynamic Programming & TD MethodsWeek 7 : Eligibility TracesWeek 8 : Function ApproximationWeek 9: Least Squares MethodsWeek 10: Fitted Q, DQN & Policy Gradient for Full RLWeek 11: Hierarchical RLWeek 12: POMDPs