Advanced · Reinforcement Learning
Markov decision process (MDP)
Visual diagram · (in preparation) · Math · (in preparation) · Worked example · 3 difficulty levels.
TL;DR. A framework for modeling decision-making in random environments where outcomes depend on both controllable actions and chance.
Technical Definition
A framework for modeling decision-making in random environments where outcomes depend on both controllable actions and chance.
How it works
A Markov Decision Process (MDP) is a mathematical framework used for modeling decision-making in situations with uncertain outcomes. It involves an agent interacting with an environment, taking actions that lead to new states and rewards, where the next state and reward probabilities depend only on the current state and action. MDPs are fundamental to reinforcement learning.
Related Concepts
- Reinforcement Learning — A paradigm where an agent learns to make decisions by receiving rewards or penalties from its environment through trial and error.
- AI Agent — An AI system that autonomously plans, uses tools, and takes actions to accomplish goals through iterative reasoning.