BELLMAN'S OPTIMAL PRINCIPLE IN AVERAGE COST PROBLEM  

作　　者：刘建庸 刘克 

机构地区：[1]Institute of Applied Mathematics, Academia Sinica, Beijing 100080, PRC

出　　处：《Chinese Science Bulletin》1990年第11期957-958,共2页

基　　金：Project supported by the National Natural Science Foundation of China

摘　　要：Our average MDP is{S, (A(i), i∈S), q, r (?)/V}, where the state space S and all action sets A(i)are nonempty countable, q is the family of stationary one-step transition laws, r is one-step reward and is uniformly bounded. Let ∏ and ∏_s^d denote respectively the general policy set and stationary policy set. π∈∏, i∈S,

关 键 词：STATIONARY nonempty UNIFORMLY COST Bellman INFERIOR assume 卜工 holds 川北 

分 类 号：N[自然科学总论]