AlphaGo and AlphaZero Quiz

Answers and explanations appear as you take the quiz.

1. Why was the game of Go considered especially hard for computers?
   • It has an astronomically large number of possible positions
   • It has very few possible moves
   • It is played only on paper
   • It has no rules
2. Who did AlphaGo famously defeat 4-1 in 2016?
   • Garry Kasparov
   • Lee Sedol
   • Magnus Carlsen
   • A random amateur
3. Which three games did AlphaZero’s paper evaluate?
   • Go, chess, and shogi
   • Poker, bridge, and backgammon
   • Atari, StarCraft, and Dota
   • Only Go and chess
4. Which search method does AlphaZero pair with its neural network?
   • Binary search of a phone book
   • Linear regression
   • Bubble sort
   • Monte Carlo Tree Search
5. What two things does AlphaZero's neural network predict to guide its search?
   • A policy (good moves) and a value (who is winning)
   • The weather and the time
   • The opponent's name and age
   • Colors and sounds
6. What did MuZero add to the AlphaZero-style planning approach?
   • A requirement for human game records
   • A learned model of reward and environment dynamics used for planning without being given the rules
   • A replacement for all tree search
   • A fixed database of every possible board position
7. What information did AlphaZero need in its board-game experiments besides self-play?
   • A database of professional games
   • A complete endgame table for every position
   • The rules of the games
   • Human rankings for every possible move
8. How did the original AlphaGo system combine supervised and reinforcement learning?
   • It trained a policy from expert games and then improved through self-play
   • It used only random moves and never trained on human games
   • It learned the game rules from images without playing
   • It relied only on a fixed database of winning games