K V Subrahmanyam

Regret analysis of stochastic and non stochastic multi-armed bandit problems by Sebastien Buebeck and Nicolo Cesa-Bianchi Lecture 2, MDP-s basics Lecture 3, Policy Iteration, Chernoff bounds, Q value iteration Lecture 4, Q value iteration, Induced MDP Lecture 5, Induced MDP, Implicit explore exploit Lecture 6, Fredman's inequality Lecture 7, Analysis of R-max Lecture 9, Policy gradient, REINFORCE Lecture 10, SARSA, Function approximators, TD Lecture 11, TD, Monte Carlo function approximators, Batch reinforcement, DQNN Lecture 12, Multi armed bandits Video recording Lecture 13, Stochastic bandits Video recording Lecture 14, UCB Video recording Lecture 15, Adversarial bandits Video recording Lecture 16, Exp-3 analysis Video recording Lecture 17, Contextual bandits Video recording Lecture 18, EXP-4 Video recording

saved by

• 5281