Hands-On Machine Learning for Algorithmic Trading

Finite MDPs

MDPs frame the agent-environment interaction as a sequential decision problem over a series of time steps t=1, ..., T, that constitute an episode. Time steps are assumed to be discrete, but the framework can be extended to continuous time.

The abstraction afforded by MDPs makes its application easily adaptable to many contexts. The time steps can be at arbitrary intervals, and actions and states can take any form that can be expressed numerically.

The Markov property implies that the current state completely describes the process, that is, the process has no memory. Information from past states adds no value when trying to predict the process' future. Due to these properties, the framework has been used to model asset prices they ...