信號(hào)博弈中的收益信息與學(xué)習(xí)

是 否 +2 論壇幣

k人 參與回答

經(jīng)管之家送您一份

應(yīng)屆畢業(yè)生專(zhuān)屬福利!

求職就業(yè)群

趙安豆老師微信：zhaoandou666

經(jīng)管之家聯(lián)合CDA

送您一個(gè)全額獎(jiǎng)學(xué)金名額~ !

立即領(lǐng)取

感謝您參與論壇問(wèn)題回答

經(jīng)管之家送您兩個(gè)論壇幣！

+2 論壇幣

摘要翻譯：
我們?cè)谛盘?hào)博弈的非均衡學(xué)習(xí)模型中加入了參與者知道對(duì)手的收益函數(shù)和合理性的假設(shè)。代理人是天生的球員角色，每個(gè)時(shí)期與隨機(jī)對(duì)手比賽。沒(méi)有經(jīng)驗(yàn)的代理人不確定對(duì)手游戲的普遍分布，但相信對(duì)手從不選擇有條件支配的策略。代理參與主動(dòng)學(xué)習(xí)，并根據(jù)個(gè)人觀察更新信念。回報(bào)信息可以改進(jìn)或擴(kuò)大學(xué)習(xí)預(yù)測(cè)，因?yàn)橛心托牡哪贻p發(fā)送者的實(shí)驗(yàn)動(dòng)機(jī)取決于他們認(rèn)為哪些接收者的反應(yīng)是合理的。我們證明了在有收益知識(shí)的情況下，長(zhǎng)期學(xué)習(xí)結(jié)果的極限集上有界于理性相容均衡(RCE)，下有界于一致RCE。RCE完善了直覺(jué)標(biāo)準(zhǔn)（Cho和Kreps，1987)，并包括所有的神平衡（Banks和Sobel，1987)。均勻的RCE有時(shí)但不總是存在，并暗示著普遍的神圣平衡。
---
英文標(biāo)題：
《Payoff Information and Learning in Signaling Games》
---
作者：
Drew Fudenberg, Kevin He
---
最新提交年份：
2020
---
分類(lèi)信息：

一級(jí)分類(lèi)：Economics        經(jīng)濟(jì)學(xué)
二級(jí)分類(lèi)：Theoretical Economics        理論經(jīng)濟(jì)學(xué)
分類(lèi)描述：Includes theoretical contributions to Contract Theory, Decision Theory, Game Theory, General Equilibrium, Growth, Learning and Evolution, Macroeconomics, Market and Mechanism Design, and Social Choice.
包括對(duì)契約理論、決策理論、博弈論、一般均衡、增長(zhǎng)、學(xué)習(xí)與進(jìn)化、宏觀經(jīng)濟(jì)學(xué)、市場(chǎng)與機(jī)制設(shè)計(jì)、社會(huì)選擇的理論貢獻(xiàn)。
--

---
英文摘要：
  We add the assumption that players know their opponents' payoff functions and rationality to a model of non-equilibrium learning in signaling games. Agents are born into player roles and play against random opponents every period. Inexperienced agents are uncertain about the prevailing distribution of opponents' play, but believe that opponents never choose conditionally dominated strategies. Agents engage in active learning and update beliefs based on personal observations. Payoff information can refine or expand learning predictions, since patient young senders' experimentation incentives depend on which receiver responses they deem plausible. We show that with payoff knowledge, the limiting set of long-run learning outcomes is bounded above by rationality-compatible equilibria (RCE), and bounded below by uniform RCE. RCE refine the Intuitive Criterion (Cho and Kreps, 1987) and include all divine equilibria (Banks and Sobel, 1987). Uniform RCE sometimes but not always exists, and implies universally divine equilibrium.
---
PDF鏈接：
https://arxiv.org/pdf/1709.01024

掃碼加我 拉你入群

請(qǐng)注明：姓名-公司-職位

以便審核進(jìn)群資格，未注明則拒絕

分享0 收藏0 回帖

關(guān)鍵詞：信號(hào)博弈 observations Contribution distribution equilibrium 下有 but 對(duì)手 refine 取決于