Intuitive RL: Intro to Advantage-Actor-Critic (A2C)

Rudy Gilman


Reinforcement learning (RL) practitioners have produced a number of excellent tutorials. Most, however, describe RL in terms of mathematical equations and abstract diagrams. We like to think of the field from a different perspective. RL itself is inspired by how animals learn, so why not translate the underlying RL machinery back into the natural phenomena they’re designed to mimic? Humans learn best through stories.

This is a story about the Actor Advantage Critic (A2C) model. Actor-Critic models are a popular form of Policy Gradient model, which is itself a vanilla RL algorithm. If you understand the A2C, you understand deep RL.

[Updated Jan 31, 2020] Corresponding code here. For more details on RL check out OpenAI’s Spinning Up.

[Updated April 19, 2021] Download the high-res file and see more ML content at

Illustrations by @embermarke