EVERYTHING AIAI engineering, made visual
Visual edition planned
Phase 09 · Lesson 01LearnPython45 min12 lessons in phase

MDPs, States, Actions & Rewards

A Markov Decision Process is five things: states, actions, transitions, rewards, a discount. Everything in RL — Q-learning, PPO, DPO, GRPO — optimizes over this shape. Learn it once, read the rest of reinforcement learning for free.

Visual edition planned

This lesson isn’t interactive yet.

It is part of the curriculum and will get the same treatment as Phase 1 — a visual cover, hands-on labs, derivations with numeric checks and a quiz. Until then, the original lesson is the best place to read it:

Part of Phase 09Reinforcement Learning. Use the previous / next cards below to keep browsing the phase.