Материал түпнұсқа тілінде: English.
Reinforcement learning with prediction-based rewards
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.
2018 ж. 31 қазан · Дереккөз: OpenAI news
Толық мәтін дереккөзде қолжетімді.