Kuiz AlphaGo dan AlphaZero

Jawapan dan penjelasan muncul semasa anda mengambil kuiz.

1. Mengapakah permainan Go dianggap sukar untuk komputer?
   • Ia mempunyai bilangan kedudukan yang besar secara astronomi
   • Ia mempunyai sangat sedikit kemungkinan pergerakan
   • Ia dimainkan hanya di atas kertas
   • Ia tidak mempunyai peraturan
2. Siapa yang terkenal dengan kekalahan AlphaGo 4-1 pada 2016?
   • Garry Kasparov
   • Lee Sedol
   • Magnus Carlsen
   • Seorang amatur rawak
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. Kaedah carian manakah yang AlphaZero berpasangan dengan rangkaian sarafnya?
   • Carian binari buku telefon
   • Regresi linear
   • Isih gelembung
   • Carian Pokok Monte Carlo
5. Apakah dua perkara yang diramalkan oleh rangkaian saraf AlphaZero untuk membimbing cariannya?
   • Dasar (pergerakan yang baik) dan nilai (siapa yang menang)
   • Cuaca dan masa
   • Nama dan umur lawan
   • Warna dan bunyi
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