Using Deep Reinforcement Learning with Hierarchical Risk Parity for Portfolio Optimization
نویسندگان
چکیده
We devise a hierarchical decision-making architecture for portfolio optimization on multiple markets. At the highest level Deep Reinforcement Learning (DRL) agent selects among number of discrete actions, representing low-level agents. For agents, we use set Hierarchical Risk Parity (HRP) and Equal Contribution (HERC) models with different hyperparameters, which all run in parallel, off-market (in simulation). The information DRL decides agents should act next is constituted by stacking recent performances Thus, modelling resembles statefull, non-stationary, multi-arm bandit, where performance individual arms changes time assumed to be dependent history. perform experiments cryptocurrency market (117 assets), stock (46 assets) foreign exchange (28 pairs) showing excellent robustness overall system. Moreover, eliminate need retraining are able deal large testing sets successfully.
منابع مشابه
Hierarchical Object Detection with Deep Reinforcement Learning
We present a method for performing hierarchical object detection in images guided by a deep reinforcement learning agent. The key idea is to focus on those parts of the image that contain richer information and zoom on them. We train an intelligent agent that, given an image window, is capable of deciding where to focus the attention among five different predefined region candidates (smaller wi...
متن کاملLearning State Representations for Query Optimization with Deep Reinforcement Learning
Deep reinforcement learning is quickly changing the field of artificial intelligence. These models are able to capture a high level understanding of their environment, enabling them to learn difficult dynamic tasks in a variety of domains. In the database field, query optimization remains a difficult problem. Our goal in this work is to explore the capabilities of deep reinforcement learning in...
متن کاملHierarchical Functional Concepts for Knowledge Transfer among Reinforcement Learning Agents
This article introduces the notions of functional space and concept as a way of knowledge representation and abstraction for Reinforcement Learning agents. These definitions are used as a tool of knowledge transfer among agents. The agents are assumed to be heterogeneous; they have different state spaces but share a same dynamic, reward and action space. In other words, the agents are assumed t...
متن کاملKnowledge Transfer for Deep Reinforcement Learning with Hierarchical Experience Replay
The process for transferring knowledge of multiple reinforcement learning policies into a single multi-task policy via distillation technique is known as policy distillation. When policy distillation is under a deep reinforcement learning setting, due to the giant parameter size and the huge state space for each task domain, it requires extensive computational efforts to train the multi-task po...
متن کاملUsing MODEA and MODM with Different Risk Measures for Portfolio Optimization
The purpose of this study is to develop portfolio optimization and assets allocation using our proposed models. The study is based on a non-parametric efficiency analysis tool, namely Data Envelopment Analysis (DEA). Conventional DEA models assume non-negative data for inputs and outputs. However, many of these data take the negative value, therefore we propose the MeanSharp-βRisk (MShβR) model...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: International Journal of Financial Studies
سال: 2022
ISSN: ['2227-7072']
DOI: https://doi.org/10.3390/ijfs11010010