The problem is set up as a reinforcement learning problem, with a trial and error method. The environment is described using state_values state_values (?), and the state_values are changed by actions. The actions are determined by an algorithm, based on the current state_value, in order to achieve a particular state_value that is termed a Markov model. In an ideal case, the past state_values does have an influence on future state_values, but here, we assume that the current state_value has all of the previous state_values encoded. There are two types of state_values; one is observable, and the other is non-observable. The model has to take non-observable state_values into account, as well. That is called a Hidden Markov model ...
Markov models
Get Python Reinforcement Learning Projects now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.