Deep Reinforcement Learning For Trading - A Critical Survey

Millea, Adrian

doi:10.20944/preprints202111.0044.v1

Cited by 12 publications

(4 citation statements)

References 40 publications

(49 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…RL has been extensively applied to stock portfolio management [20,21,22,23,24,25], but not yet to holistic asset management; the lack of model transparency may be a contributing factor. Interpretation of RL agents typically follows model training [26,27,28]; our ambition is to impose a desired characteristic behaviour during training, thus making it an intrinsic property of the agent.…”

Section: Related Workmentioning

confidence: 99%

Can Interpretable Reinforcement Learning Manage Prosperity Your Way?

Maree,

Omlin

2022

Preprint

View full text Add to dashboard Cite

Personalisation of products and services is fast becoming the driver of success in banking and commerce. Machine learning holds the promise of gaining a deeper understanding of and tailoring to customers' needs and preferences. Whereas traditional solutions to financial decision problems frequently rely on model assumptions, reinforcement learning is able to exploit large amounts of data to improve customer modelling and decisionmaking in complex financial environments with fewer assumptions. Model explainability and interpretability present challenges from a regulatory perspective which demands transparency for acceptance; they also offer the opportunity for improved insight into and understanding of customers. Post-hoc approaches are typically used for explaining pretrained reinforcement learning models. Based on our previous modeling of customer spending behaviour, we adapt our recent reinforcement learning algorithm that intrinsically characterizes desirable behaviours and we transition to the problem of asset management. We train inherently interpretable reinforcement learning agents to give investment advice that is aligned with prototype financial personality traits which are combined to make a final recommendation. We observe that the trained agents' advice adheres to their intended characteristics, they learn the value of compound growth, and, without any explicit reference, the notion of risk as well as improved policy convergence.

show abstract

Section: Related Workmentioning

confidence: 99%

Can Interpretable Reinforcement Learning Manage Prosperity Your Way?

Maree,

Omlin

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…For more general ML information, Kumbure et al [45] reviews the literature and ML techniques and data for stock market forecasting. Millea [45] offers a critical survey of deep reinforcement for trading [46]. Taghian et al [48] proposed a DRL model with feature extraction modules on the Dow Jones Index.…”

Section: Related Workmentioning

confidence: 99%

Multi-Timeframe Algorithmic Trading Bots Using Thick Data Heuristics with Deep Reinforcement Learning

Roy

Mohammed

2022

Artificial Intelligence Evolution

View full text Add to dashboard Cite

This article presents an augmented Artificial Intelligence (AI) algorithmic trading approach that combines Thick Data Heuristic (TDH), with Deep Reinforcement Learning (DRL), to successfully learn trading execution timing policies. Combining the augmented AI human trader's intuition and heuristics with DRL techniques to provide more focused drivers for trading order execution timing is explored in this study. In this research, the goal is to solve the sequential decision-making problem of AI for profitable day and swing trading order timing executions. Enabling trading bots with cognitive intelligence and common-sense heuristics will offer traders including automatic traders an insight to understand the day-to-day swing trading timeframes indicators and arrive at mature trading decision-making. This article examines the performance of bots with Nasdaq and NYSE stocks that have a strong catalyst (info. which increases directional momentum) to find that they outperform benchmark algorithmic trading approaches. The research illustrates to the reader how to combine TDH and Deep Q-networks (DQN) into a TDH-DQN augmented AI trading bot. The bot learns through test data to predict the optimal timing of order executions autonomously on idealized trading time series data.

show abstract

“…Although artificial intelligence (AI) has become a ubiquitous tool in financial technology [2], research in the field has yet to significantly advance levels of personalization [3]. Asset management is an active research topic in AI for finance; however, the research opportunities presented by the need for personalized services are usually neglected [4]. Whereas personalized investment advice is typically based on questionnaires, we propose the use of micro-segmentation based on spending behavior.…”

Section: Introductionmentioning

confidence: 99%

Reinforcement Learning with Intrinsic Affinity for Personalized Prosperity Management

Maree¹,

Omlin²

2022

Preprint

View full text Add to dashboard Cite

The common purpose of applying reinforcement learning (RL) to asset management is the maximization of profit. The extrinsic reward function used to learn an optimal strategy typically does not take into account any other preferences or constraints. We have developed a regularization method that ensures that strategies have global intrinsic affinities, i.e., different personalities may have preferences for certain assets which may change over time. We capitalize on these intrinsic policy affinities to make our RL model inherently interpretable. We demonstrate how RL agents can be trained to orchestrate such individual policies for particular personality profiles and still achieve high returns.

show abstract

Deep Reinforcement Learning For Trading - A Critical Survey

Cited by 12 publications

References 40 publications

Can Interpretable Reinforcement Learning Manage Prosperity Your Way?

Can Interpretable Reinforcement Learning Manage Prosperity Your Way?

Multi-Timeframe Algorithmic Trading Bots Using Thick Data Heuristics with Deep Reinforcement Learning

Reinforcement Learning with Intrinsic Affinity for Personalized Prosperity Management

Contact Info

Product

Resources

About