دانلود مقاله انگلیسی رایگان:کنترل مداوم با یادگیری تقویتی مجدد پویا عمیق انباشته برای بهینه سازی نمونه کارها - 2020
بلافاصله پس از پرداخت دانلود کنید
دانلود مقاله انگلیسی یادگیری تقویتی رایگان
  • Continuous control with Stacked Deep Dynamic Recurrent Reinforcement Learning for portfolio optimization Continuous control with Stacked Deep Dynamic Recurrent Reinforcement Learning for portfolio optimization
    Continuous control with Stacked Deep Dynamic Recurrent Reinforcement Learning for portfolio optimization

    سال انتشار:

    2020


    عنوان انگلیسی مقاله:

    Continuous control with Stacked Deep Dynamic Recurrent Reinforcement Learning for portfolio optimization


    ترجمه فارسی عنوان مقاله:

    کنترل مداوم با یادگیری تقویتی مجدد پویا عمیق انباشته برای بهینه سازی نمونه کارها


    منبع:

    Sciencedirect - Elsevier - Expert Systems With Applications, 140 (2020) 112891. doi:10.1016/j.eswa.2019.112891


    نویسنده:

    Amine Mohamed Aboussalah, Chi-Guhn Lee


    چکیده انگلیسی:

    Recurrent reinforcement learning (RRL) techniques have been used to optimize asset trading systems and have achieved outstanding results. However, the majority of the previous work has been dedicated to sys- tems with discrete action spaces. To address the challenge of continuous action and multi-dimensional state spaces, we propose the so called Stacked Deep Dynamic Recurrent Reinforcement Learning (SDDRRL) architecture to construct a real-time optimal portfolio. The algorithm captures the up-to-date market con- ditions and rebalances the portfolio accordingly. Under this general vision, Sharpe ratio, which is one of the most widely accepted measures of risk-adjusted returns, has been used as a performance metric. Ad- ditionally, the performance of most machine learning algorithms highly depends on their hyperparameter settings. Therefore, we equipped SDDRRL with the ability to find the best possible architecture topology using an automated Gaussian Process ( GP ) with Expected Improvement ( EI ) as an acquisition function. This allows us to select the best architectures that maximizes the total return while respecting the car- dinality constraints. Finally, our system was trained and tested in an online manner for 20 successive rounds with data for ten selected stocks from different sectors of the S&P 500 from January 1st, 2013 to July 31st, 2017. The experiments reveal that the proposed SDDRRL achieves superior performance com- pared to three benchmarks: the rolling horizon Mean-Variance Optimization (MVO) model, the rolling horizon risk parity model, and the uniform buy-and-hold (UBAH) index.
    Keywords: Reinforcement learning | Policy gradient | Deep learning | Sequential model-based optimization | Financial time series | Portfolio management | Trading systems


    سطح: متوسط
    تعداد صفحات فایل pdf انگلیسی: 11
    حجم فایل: 2628 کیلوبایت

    قیمت: رایگان


    توضیحات اضافی:




اگر این مقاله را پسندیدید آن را در شبکه های اجتماعی به اشتراک بگذارید (برای به اشتراک گذاری بر روی ایکن های زیر کلیک کنید)

تعداد نظرات : 0

الزامی
الزامی
الزامی
rss مقالات ترجمه شده rss مقالات انگلیسی rss کتاب های انگلیسی rss مقالات آموزشی
logo-samandehi