← Back to Data Science

All Topics

Advertisement

Learn/Data Science/Machine Learning

Markov Decision Processes

Topic: RL

Advertisement

MDP Fundamentals

Foundation for RL problems.

Components

States. Actions. Transitions. Rewards. γ discount factor.

Markov Property

Future depends only on current state.

Goal

Maximize expected cumulative reward.

Key Takeaways

  1. MDP components
  2. Markov property
  3. Maximize cumulative reward

Advertisement

Advertisement

Need More Practice?

Get personalized data science help from ChatWhole's AI-powered platform.

Get Expert Help →