QUANT[17]強化學習(Reinforcement Learning)學習筆記5

Reinforcement Learning:An Introduction NOTE[3] 1.3 Elements of Reinforcement Learning RL四要素: 1. policy: 定義了learning agent在特定時刻的行爲表現。 2. reward signal: 定義了RL problem的目標,反映了what is good in an immediate
相關文章
相關標籤/搜索