Meta-learning for wrestling
核心要点速览
We show that for the task of simulated robot wrestling, a meta-learning agent can learn to quickly defeat a stronger non-meta-learning agent, and also show that the meta-learning agent can adapt to physical malfunction.
查看完整报道与分享
完整图文、背景资料与讨论归原始发布平台 OpenAI News 所有。