-
Book Overview & Buying
-
Table Of Contents
Hands-On Artificial Intelligence for IoT - Second Edition
By :
In his doctoral thesis titled Learning from delayed rewards (1989), Watkins introduced the concept of Q-learning. The goal of Q-learning is to learn an optimal action selection policy. Given a specific state, s, and taking a specific action, a, Q-learning attempts to learn the value of the state s. In its simplest version, Q-learning can be implemented with the help of look-up tables. We maintain a table of values for every state (row) and action (column) possible in the environment. The algorithm attempts to learn the value—that is, how good of an idea it is to take a particular action in the given state.
We start by initializing all of the entries in the Q-table to zero; this ensures all states have a uniform (and hence equal chance) value. Later, we observe the rewards obtained by taking a particular action and, based on the rewards, we update the Q-table. The update in Q-value is performed dynamically with the help of the Bellman equation, given by the following...