OpenAI News·· 2017-10-11AI 评分38
OpenAI 发现自我博弈助 AI 习得足球技能
Competitive self-play
AI 导读
OpenAI 发现自我博弈使模拟 AI 无需预设环境即可自主习得铲球、假动作等足球物理技能。该方法确保训练难度始终适配 AI 能力,结合 Dota 2 结果增强了对自我博弈作为未来核心 AI 组件的信心。
原文
We’ve found that self-play allows simulated AIs to discover physical skills like tackling, ducking, faking, kicking, catching, and diving for the ball, without explicitly designing an environment with these skills in mind. Self-play ensures that the environment is always the right difficulty for an AI to improve. Taken alongside our Dota 2 self-play results, we have increasing confidence that self-play will be a core part of powerful AI systems in the future.
来源:OpenAI News · openai.com