Reinforcement Learning
An agent acts, gets a reward, and improves a policy by trial and error — sequential decisions on a tiny grid on ExamMaster.
Undergraduate depth: concept notes and, where they help, in-browser labs. Reading is free.
Lessons
- Agent, environment, state, actionIn Reinforcement Learning because the agent, the floor, the cell you stand on, and the step you take are the four pieces of the loop.
- A tiny update loopIn Reinforcement Learning because the table of values improves from the walk you just took, one update at a time.
- A policy is a rule per cellIn Reinforcement Learning because a policy is the rule that picks the next step from the cell you are in.
- Reward now, return laterIn Reinforcement Learning because a single step's reward is not the score of a path — the return is.
- Value is how good a cell isIn Reinforcement Learning because a value is how good a cell (or a step from a cell) is — a number, not a neural net.
- What reinforcement learning isIn Reinforcement Learning because the job is to act, see a reward, and try again — not to fit a predictor from a ready table.
Practise Reinforcement Learning
Reading every chapter below is free and needs no account. Practice, mocks and progress live in the app.
Continue with Google — freeNo card, no trial. Works offline once installed.