OPERNEX LEARNING

Learn Agentic AI

A structured, practical learning path from language model foundations to intelligent agentic systems.

6 Learning parts
453 Subtopics
415 Published lessons
Foundations / Introduction to Reinforcement Learning / The Markov Decision Process (MDP)
Lesson 101 of 415 5 min read
3.1.3

State Space and Action Space

Understand the possible situations an agent can observe and the actions it can choose.

What is it?

The state space represents all possible situations an agent may encounter. The action space represents the decisions available to the agent.

Key points

1. State represents the current situation. 2. State space is denoted by S. 3. Action represents an agent decision. 4. Action space is denoted by A. 5. Available actions may depend on the current state. 6. A policy guides action selection.

Example: State and action in a delivery robot

Possible states: • Near shelf A. • Near shelf B. • At the packing station. Possible actions: • Move forward. • Turn left. • Turn right. • Pick up a package.

Real-world application

State and action spaces are essential when designing robotics, warehouse automation and game environments.
Key takeaway

The state describes the situation; the action describes what the agent can do.