Skip to content
AI-grafen
Sign in
☰ Menu

The goal E University

Train an agent with reward

From bandits to policy gradient: build an environment, let an agent learn from reward, and understand why RL is hard.

Knowledge nodes
31
From zero
about 18 h
Labs
6
See what you already know — no account

The diagnostic removes what you already know, so your path is usually much shorter.

What you can do afterwards

Labs along the way

You write the code. Tests you cannot see decide whether it holds up.

Lab: gradient descent from scratchDin the browser · about 50 minLab: lists, loops and dictionariesCin the browser · about 40 minLab: mean, median and standard deviation by handCin the browser · about 40 minLab: simulate dice and compare with the theoryCin the browser · about 40 minLab: the best line with least squaresCin the browser · about 40 minLab: your first Python functionsCin the browser · about 30 min

The whole path

Everything the goal builds on, grouped by level and in the order it builds on itself. Show on the map

AExplorer4 knowledge nodes
  1. Patterns and categories
  2. Probability and risk in everyday life
  3. Sequences and precise instructions
  4. Controlling a process with commands
BInvestigator8 knowledge nodes
  1. Data in everyday life
  2. Algorithmic thinking
  3. Rule-based systems and machine learning
  4. Reinforcement learning: learning from feedback
  5. When AI optimises the wrong metric
  6. Randomness and probability: basic calculations
  7. Training data, features and labels
  8. Classification: how a model sorts information
CBuilder8 knowledge nodes
  1. Functions and coordinate systems
  2. Programming logic — variables, conditions, loops
  3. Python — the basics
  4. Python — lists, loops and dictionaries
  5. Statistics — mean, median and spread
  6. Probability — the basics
  7. Linear regression: fitting a straight line to data
  8. Try something new or play it safe?
DAI developer6 knowledge nodes
  1. Derivatives and optimisation
  2. Python — functions, scope and exceptions
  3. Python — classes and objects
  4. Conditional probability
  5. Gradient descent
  6. The grid world: your first RL agent
EUniversity5 knowledge nodes
  1. Environments and simulation
  2. Multi-armed bandits
  3. Reinforcement learning — the basics
  4. Markov decision processes
  5. Q-learning