OpenAI 的 Dota 2 機械人在標準賽事規則 1v1 對局中擊敗世界頂尖職業選手
Dota 2
OpenAI 開發的 Dota 2 機械人在遵循標準賽事規則的 1v1 對局中擊敗世界頂尖職業選手。機械人從零開始透過自我對弈學習,沒有使用模仿學習或樹搜索。OpenAI 將此視為朝建立能在涉及真實人類的混亂複雜情境中完成明確目標的 AI 系統邁出的一步。
這則公告同時交代對局成果與訓練方式,呈現自我對弈在規則明確、局勢複雜且有人類參與的遊戲環境中的應用。
Dota 2

Loading…
Share
We’ve created a bot which beats the world’s top professionals at 1v1 matches of Dota 2 under standard tournament rules. The bot learned the game from scratch by self-play, and does not use imitation learning or tree search. This is a step towards building AI systems which accomplish well-defined goals in messy, complicated situations involving real humans.
Today we playedDendi(opens in a new window)on mainstage atThe International(opens in a new window), winning a best-of-three match. Over the past week, our bot was undefeated against many top professionals includingSumaiL(opens in a new window)(top 1v1 player in the world) andArteezy(opens in a new window)(top overall player in the world).
Dota 1v1 is a complex game with hidden information. Agents must learn to plan, attack, trick, and deceive their opponents. The correlation between player skill and actions-per-minute is not strong, and in fact, our AI’s actions-per-minute are comparable to that of an average human player.
Success in Dota requires players to develop intuitions about their opponents and plan accordingly. In the above video you can see that our bot has learned—entirely via self-play—to predict where other players will move, to improvise in response to unfamiliar situations, and how to influence the other player’s allied units to help it succeed.
The full game of Dota is played by two teams of five. Each player chooses from a hundred heroes and hundreds of items. Our next step is to create a team of Dota 2 bots which can compete and collaborate with the top human teams. If you’d like to work on the next phase of the project, considerjoining OpenAI.
Author
OpenAI
來源:OpenAI News · openai.com