Deep reinforcement learning main components that enable the estimation of the expected reward of any action of the action space of the agent conditioned to any state perceived by the agent.

Deep reinforcement learning main components that enable the estimation of the expected reward of any action of the action space of the agent conditioned to any state perceived by the agent.

<p>The learnt policy function is encoded by a deep neural network, enabling continuous-valued actions and spaces and any complexity of its mapping.</p>

محفوظ في:

التفاصيل البيبلوغرافية
المؤلف الرئيسي:	Alejandra de-la-Rica-Escudero (20570535) (author)
مؤلفون آخرون:	Eduardo C. Garrido-Merchán (18830597) (author), María Coronado-Vaca (20570538) (author)
منشور في:	2025
الموضوعات:	Science Policy Virology Environmental Sciences not elsewhere classified Biological Sciences not elsewhere classified Mathematical Sciences not elsewhere classified successfully addressed recently high volatility markets every action performed deep reinforcement learning also called gymnasium universal approximator models markowitz model rely proximal policy optimization novel explainable drl making drl explainable drl algorithms train agent &# 8217 methods rely alternative models investment policy drl algorithm drl agents technological sector quantitative researchers portfolio management financial state feature importance expected reward enhance transparency empirically illustrate
الوسوم:	إضافة وسم لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!

Cannot write session to /tmp/vufind_sessions/sess_4v53cdqurrrjoo7bu8bd1bup5h