Reinforcement learning with prediction-based rewards
核心要点速览
We’ve developed Random Network Distillation (RND), a prediction-based method for encouraging reinforcement learning agents to explore their environments through curiosity, which for the first time exceeds average human performance on Montezuma’s Revenge.
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。