stochastic game 中文意思是什麼
stochastic game
解釋
隨機對策- stochastic : adj. 1. 機會的；有可能性的;隨便的。2. 【數學】隨機的。
- game : n 1 游戲；娛樂；戲謔；運動。2 （運動、棋類等的）比賽，競賽；（比賽中的）一盤，一場，一局；勝利；...
-
After introducing some basic concepts of agent 、 mas and multi - agents learning, the thesis analyses the research actuality and the future developmental directions of rl and multi - agent rl ( marl ). furthermore, the theory and related learning algorithms of them are briefly introduced. on the basis of analyses of pursuit game, aimed at the individual action learner, the thesis extends the rl algorithm for single agent, proposes the macrl - cc algorithm. finally, aimed at the joint action learner, a team - stochastic - games - based ( tsgs - based ) framework for multi - agents cooperative rl is defined
文章首先介紹了agent和多agent系統、以及多agent學習的一些基本概念，然後介紹了強化學習和多agent強化學習的研究現狀和未來發展方向。第二部分對強化學習理論和多agent強化學習理論進行了簡要介紹。在對pursuitgame問題進行初步分析的基礎上，針對獨立行為學習者，擴展了單agent強化學習演算法，提出了基於承諾和約定的多agent協同強化學習方法macrl - cc 。 -
The simulation findings uncover that : either a higher inefficiency level of e - marketplace, or a higher opportunity cost that a seller in the traditional marketplace takes, or a low upper limit of active sellers in e - marketplace, or a higher probability of taking stochastic actions, or less information to form expectation, can be propitious for spurring the shift from the traditional marketplace to the e - marketplace. as for the popular “ thorough shift ” presumption, this paper puts forward that, an aggressive shift from traditional marketplace to e - marketplace is probably built on an effort by the buyer to constrain his own bargaining power or to share benefits with the supplier. by developing economic models and leveraging the general game theory, this paper also finds out that cost is the critical factor that governs the evolution of monopolistic market, monopolistic competitive market and oligarchic market
保持其它因素不變，以上因素對市場演化的影響作用分別為:市場演化對電子市場競爭無效率度高度敏感，當電子市場競爭無效率度小幅度下降時，市場顯著地偏向傳統市場，當電子市場競爭無效率度小幅度上升時，市場顯著地偏向電子市場;傳統交易中賣方所承擔的隱性成本是市場演化的另一個決定性因素，當傳統交易中的賣方所承擔的隱性成本取值較大時，電子市場將佔主導地位，當傳統交易中的賣方所承擔的隱性成本取值較小時，傳統市場將佔主導地位， ;當為電子市場中實際參與每筆交易的賣方設置一個低的上限時，傳統市場將迅速演化為電子市場;市場參與者的非理性行動概率越大，市場越容易向電子市場 -
In order to solve the multi - equilibria problem in the stochastic games, a macrl algorithm called macrl - japs is proposed. these two learning methods have been justified by experiments. the main research achievements and innovations are the establishment of two macrl methods for pursuit game, which are justified by experiments
針對聯合行為學習者，給出了多agent協同強化學習的團隊隨機博弈框架，並解決了多最優均衡解問題，提出了基於聯合行為優先序列的多agent協同強化學習方法macrl - japs 。 -
Combining forward and backward stochastic differential equations and filtering techniques, the nash equilibrium point of a type of partially observed lq nonzero sum stochastic differential game problem is obtained
摘要結合正倒向隨機微分方程理論和濾波技術，給出了一類部分可觀測信息下線性二次非零和隨機微分對策問題的納什均衡點。
分享友人