YOUR FOUNDATION-FIRST SYLLABUS
Games, planning & decisions
Start with a small game or a choice between actions. Explore possible next steps, compare plans, and learn how experience can change which action a system chooses.
0 of 34 core ideas demonstrated34 lessons410 estimated minutes remaining
Already know some of this?
Go straight to an idea’s knowledge check. Passing its different checks without hints carries that evidence into this path. Checking an advanced idea does not award its prerequisites; you can still explore them.
Check what I already knowTHE IDEAS, IN ORDER
Shared credit is automaticBuild your understanding.
Chapter counts use compatible knowledge-check evidence. Reading a lesson does not mark its ideas as demonstrated.
Chapter 1 · Lessons 1–7 Meet an AI system Start with an everyday task, then follow its inputs, model, and output. 7 lessons · 0 of 7 core ideas demonstrated Up next
01
What is AI? Start with an everyday task Common Ground · 11 min
To explore02 Inputs and outputs: what goes in and what comes out Common Ground · 13 min
To explore03 Data and examples: what a computer can learn from Common Ground · 10 min
To explore04 What is a model? A small rule inside a bigger app Common Ground · 10 min
To explore05 Weights: the adjustable numbers in a model Common Ground · 12 min
To explore06 Training and inference: changing a rule or using it Common Ground · 13 min
To explore07 Follow one small AI system from start to finish Common Ground · 9 min
To exploreChapter 2 · Lessons 8–13 How computers represent a problem Explore everyday AI ideas; how AI got here; how computers represent a problem. 6 lessons · 0 of 6 core ideas demonstrated
08
Different ways to solve the same problem Common Ground · 11 min
To explore09 How to tell whether an AI answer is useful Common Ground · 10 min
To explore10 The questions that shaped AI Common Ground · 15 min
To explore11 How a computer stores a picture or a sentence Learning mechanisms · 16 min
To explore12 Describe a computation so someone else can follow it Learning mechanisms · 11 min
To explore13 What a representation makes easy to learn Learning mechanisms · 12 min
To exploreChapter 3 · Lessons 14–20 Searching and planning Explore searching and planning; math preparation when it is needed. 7 lessons · 0 of 7 core ideas demonstrated
14
The numbers you actually need Math preparation · 10 min
To explore15 Sets, graphs, and counting possibilities Math preparation · 10 min
To explore16 Turn a goal into states and actions Learning mechanisms · 13 min
To explore17 Choose an order for exploring possibilities Learning mechanisms · 14 min
To explore18 Use an estimate without confusing it with a guarantee Learning mechanisms · 13 min
To explore19 Probability without the mystery Math preparation · 10 min
To explore20 Value a choice and its later consequences Math preparation · 12 min
To exploreChapter 4 · Lessons 21–27 Reasoning with facts and rules Explore searching and planning; reasoning with facts and rules; learning from useful data; and supporting ideas. 7 lessons · 0 of 7 core ideas demonstrated
21
Plan while another player chooses the reply Learning mechanisms · 14 min
To explore22 Reason with statements that are true or false Learning mechanisms · 13 min
To explore23 Talk about objects and relationships Learning mechanisms · 12 min
To explore24 From facts to conclusions—and backward from a goal Learning mechanisms · 12 min
To explore25 Represent what an action requires and changes Learning mechanisms · 14 min
To explore26 Different ways to learn Common Ground · 12 min
To explore27 Learn decisions from consequences over time Learning mechanisms · 13 min
To exploreChapter 5 · Lessons 28–34 Learning through actions and rewards Explore searching and planning; learning through actions and rewards; working with uncertainty; and supporting ideas. 7 lessons · 0 of 7 core ideas demonstrated
28
Plan when you cannot see the whole state Learning mechanisms · 13 min
To explore29 Relate the value of a state to its next step Learning mechanisms · 13 min
To explore30 Averages over uncertain outcomes Math preparation · 9 min
To explore31 What can a small experiment tell us? Math preparation · 10 min
To explore32 Choose between known rewards and learning about alternatives Learning mechanisms · 13 min
To explore33 Estimate a difficult average by sampling Learning mechanisms · 12 min
To explore34 Update values from sampled transitions Learning mechanisms · 13 min
To exploreOptional extensions and comparisons (16)
These lessons deepen or compare the reference design. They do not add requirements to this path’s completion.
How to use this school without getting lostOptional orientation: how paths, side lessons, and practice fit together, plus study habits that make learning stick.Practice, progress, and knowing what you understandOptional orientation: use practice, mistakes, and spaced review to find out what you really understand.Approximate action values with a neural networkSee how tabular Q-learning scales to camera images, the approach behind DQN's Atari results.Learn a policy directly from its outcomesLearn policies directly instead of values: REINFORCE, actor-critic, and PPO, the algorithm used in RLHF for chat models.Learn when other decision-makers are learning tooLearning when opponents learn too: self-play, equilibria, and moving targets.Search with a population of varied candidatesSearch by mutation and selection when there's no gradient to follow.Represent graded membership without confusing it with probability'Warm-ish' and 'mostly safe': graded categories and the fuzzy controllers in everyday appliances.Search for a proof or a satisfying assignmentSAT solvers and theorem provers: search that proves an answer rather than guessing it.Reason when new facts can overturn a conclusionBirds fly, except penguins. Reasoning with rules that have exceptions, a classic AI puzzle.Search for a program that fits a specificationSearch for a program that fits examples: the idea behind Flash Fill and code-writing models.Combine explicit knowledge with learned perceptionClose the logic module with the pattern behind many modern systems: a learned model proposes, and a symbolic checker verifies.Evolve programs, weights, or architecturesEvolve programs and even neural-network architectures, and count what that search costs.Coordinate simple searchers through shared signalsParticle swarms and ant colonies: search inspired by animal groups.Reuse past cases and combine explicit knowledge with learned predictionsSolve new problems by adapting past cases, and combine rules with learned predictions.Connect learned representations with explicit reasoning constraintsCombine neural perception with logical rules and constraints.Choose a search or hybrid method for the constraints you havePick between search, evolutionary, fuzzy, and Bayesian methods for the problem in front of you.