کد مقاله | کد نشریه | سال انتشار | مقاله انگلیسی | نسخه تمام متن |
---|---|---|---|---|
10474850 | 928602 | 2005 | 36 صفحه PDF | دانلود رایگان |
عنوان انگلیسی مقاله ISI
On the convergence of reinforcement learning
دانلود مقاله + سفارش ترجمه
دانلود مقاله ISI انگلیسی
رایگان برای ایرانیان
موضوعات مرتبط
علوم انسانی و اجتماعی
اقتصاد، اقتصادسنجی و امور مالی
اقتصاد و اقتصادسنجی
پیش نمایش صفحه اول مقاله
![عکس صفحه اول مقاله: On the convergence of reinforcement learning On the convergence of reinforcement learning](/preview/png/10474850.png)
چکیده انگلیسی
This paper examines the convergence of payoffs and strategies in Erev and Roth's model of reinforcement learning. When all players use this rule it eliminates iteratively dominated strategies and in two-person constant-sum games average payoffs converge to the value of the game. Strategies converge in constant-sum games with unique equilibria if they are pure or if they are mixed and the game is 2Ã2. The long-run behaviour of the learning rule is governed by equations related to Maynard Smith's version of the replicator dynamic. Properties of the learning rule against general opponents are also studied.
ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Journal of Economic Theory - Volume 122, Issue 1, May 2005, Pages 1-36
Journal: Journal of Economic Theory - Volume 122, Issue 1, May 2005, Pages 1-36
نویسندگان
A.W. Beggs,