youtor.org
Multi armed bandits
>> YOUR LINK HERE: ___ http://youtube.com/watch?v=FIzLRb_xXF0
Mastering Reinforcement Learning • Multi-armed bandits: epsilon greedy, epsilon decreasing, softmax, and UCB1. • https://gibberblot.github.io/rl-notes/ • Tim Miller • Professor of Artificial Intelligence • The University of Queensland • https://uqtmiller.github.io/ • 0:00:00 1 Introduction to multi-armed bandits • 0:00:43 2 Intuition of multi-armed bandits • 0:01:47 3 Multi-armed bandits - Definition • 0:02:49 4 Regret and exploration vs. expoitation • 0:08:36 5 Simulation example • 0:09:54 6 Epsilon greedy • 0:11:52 7 Epsilon decreasing • 0:13:40 8 Softmax • 0:18:25 9 Upper confidence bounds • 0:22:14 10 Multi-armed bandits summary
#############################
