那个用遗传算法打星际的AI,到底多能打?
原创
2010年,加州伯克利的Overmind拿下了星际争霸AI大赛冠军。它不是那种"按流程走"的脚本bot——Overmind把神经网络和遗传算法揉在一起,让每个单位自己"学"会走位、集火、撤退。最让我感兴趣的一点:它不"理解"局势,全靠海量试错把最优策略刻进参数。这就引出一个问题:靠暴力搜索堆出来的"聪明",还算智能吗?我觉得算,但不是我们通常理解的聪明。它更像一把被磨到极致的工具,而非一个有思想的对手。
原文:How the Berkeley Overmind won the 2010 StarCraft AI competition · 来源:Hacker News
版权声明
所有资源都来源于爬虫采集,如有侵权请联系我们,我们将立即删除
相关文章
- Nvidia's Seven Billionaires Have Lost a Third of Their Wealth
- Stabyourself.net Games
- 【IT 早报】2026年11月19日 - 本周要闻与趋势
- 从均匀平铺到自适应路由:RINs 如何让扩散生成提速 10 倍?
- Claude Code makes a finished subagent send its report twice (70-second repro)
- Becerra faces a $2B budget deficit as potential AI bust looms
- Show HN: Agent Hive – cute Grokbot like agentic teams with queen and many bees
- Show HN: Lazycow Studio – turns footage you never edited into reels, locally
- Experiments in Weight-Space Programming
- Lindy Effect
最新文章
- Nvidia's Seven Billionaires Have Lost a Third of Their Wealth 41秒前
- Stabyourself.net Games 1小时前
- 【IT 早报】2026年11月19日 - 本周要闻与趋势 1小时前
- 从均匀平铺到自适应路由:RINs 如何让扩散生成提速 10 倍? 2小时前
- Claude Code makes a finished subagent send its report twice (70-second repro) 2小时前
- Becerra faces a $2B budget deficit as potential AI bust looms 2小时前
- Show HN: Agent Hive – cute Grokbot like agentic teams with queen and many bees 3小时前
- Show HN: Lazycow Studio – turns footage you never edited into reels, locally 3小时前
- Experiments in Weight-Space Programming 3小时前
- Lindy Effect 4小时前
itfan123




