OpenAI 谈多智能体环境：为争夺资源而竞争的 agent 环境是通往 AGI 路上的垫脚石。它有两个有用性质——其一有天然课程，环境难度由对手的强弱决定（与自己的克隆竞争时，难度正好匹配你的水平）；其二没有稳定均衡，agent 再聪明也总有变得更强的压力。这类环境与传统的 RL 环境感觉完全不同，要擅长它还需要大量研究
Learning to cooperate, compete, and communicate
评分 40
导读
OpenAI 论述多智能体环境（agent 之间为争夺资源而竞争）是通往 AGI 道路上的垫脚石。作者指出这类环境有两个有用性质：第一，它自带一条自然的课程——环境的难度由竞争者的水平决定，如果你与自己的克隆竞争，环境难度就恰好与你的水平相匹配；第二，多智能体环境没有稳定的均衡——无论一个 agent 有多聪明，总有让它变得更强的压力。作者说，这些环境与传统环境感觉非常不同，要真正擅长它们还需要非常多的研究。
主体与标签
OpenAI#论文/研究#Agent
正文
Multiagent environments where agents compete for resources are stepping stones on the path to AGI. Multiagent environments have two useful properties: first, there is a natural curriculum—the difficulty of the environment is determined by the skill of your competitors (and if you’re competing against clones of yourself, the environment exactly matches your skill level). Second, a multiagent environment has no stable equilibrium: no matter how smart an agent is, there’s always pressure to get smarter. These environments have a very different feel from traditional environments, and it’ll take a lot more research before we become good at them.