Michał Chromiak's blog Reinforcement learning: A practical primer on agents, returns, values, and policies
The concepts and equations needed to reason about online, offline, model-free, and model-based RL
Reinforcement learning trains an agent to make sequential decisions whose consequences may arrive much later. This primer builds the essential vocabulary, derives return and value functions, explains Bellman and temporal-difference learning, and distinguishes online from offline and model-free from model-based RL.
more ...