引導式測驗 · 中等 等級
AlphaGo 和 AlphaZero 測驗
回顧 AlphaGo 的專家對弈和自我對弈訓練、AlphaZero 基於規則的學習和搜索,以及 MuZero 的規劃學習模型。
問題 1 的 8
為什麼圍棋遊戲被認為對電腦來說特別難?
預覽每個問題8 問題
當您參加測驗時,就會出現答案和解釋。
- 為什麼圍棋遊戲被認為對電腦來說特別難?
- 它有大量的可能位置
- 它的可能動作很少
- 它只在紙上播放
- 它沒有規則
- 2016 年 AlphaGo 4-1 擊敗誰?
- 加里·卡斯帕羅夫
- 李世石
- 馬格努斯·卡爾森
- 隨機的業餘愛好者
- AlphaZero 的論文評估了哪三種遊戲?
- Go, chess, and shogi
- Poker, bridge, and backgammon
- Atari, StarCraft, and Dota
- Only Go and chess
- AlphaZero 與其神經網路配對的搜尋方法是什麼?
- 電話簿的二分查找
- 線性迴歸
- 冒泡排序
- 蒙特卡羅樹搜索
- AlphaZero 的神經網路預測哪兩件事來引導其搜尋?
- 政策(好的舉措)和價值(誰獲勝)
- 天氣和時間
- 對手的姓名和年齡
- 顏色和聲音
- 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
- 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
- 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