~ing[Survey리뷰]Deep Reinforcement Learning for Trading—A Critical Survey

Deep Reinforcement Learning for Trading—A Critical Survey

data-06-00119-v2.pdf

1.78MB

논문 내용 중 몇개만 선정해서 논문 비교 진행

 

 

 

 

no / 논문 명	Data	State Space  // Performance	논문
Deep Reinforcement Learning for Automated Stock Trading: An Ensemble Strategy [47]	30 stocks daily, 7 years	balance, shares, price technical indicators (MACD, RSI, CCI, ADX).         //          Sharpe=1.3 Annual return=13%	https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3690996
🧞‍♂️🧞🧞‍♀️Adaptive Stock Trading Strategies with Deep Reinforcement Learning Methods [63]	15 stocks daily, 8 years	OHLCV + Technical indicators (MA, EMA, MACD, BIAS, VR, and OBV)   //  3 years −6%−200%	https://www.sciencedirect.com/science/article/abs/pii/S0020025520304692?via%3Dihub
Model-based deep reinforcement learning for dynamic portfolio optimization [23]	7 stocks hourly, 14 years augmented	OHLC predicted next HLC market perf. index //                                     2 years annual return = 8%	https://arxiv.org/pdf/1901.08740.pdf
Commission fee is not enough:  A hierarchical reinforced framework for  portfolio management [25]	46 stocks daily, 14 years	LOB, OHLCV  // Wealth ≈ 200%	https://ojs.aaai.org/index.php/AAAI/article/view/16142	The high-level policy gives portfolio weights at a lower frequency to maximize the long term profit and invokes the low-level policy to sell or buy the corresponding shares within a short time window at a higher frequency to minimize the trading cost
A framework of hierarchical deep q-network for portfolio management [26]	4 Chinese stocks 2 days, 2 years	OHLC, shares   //    1 year 44%	https://www.scitepress.org/Papers/2021/102332/102332.pdf	This paper introduces a framework, based on the hierarchical Deep QNetwork, that addresses the issue of zero commission fee by reducing the number of assets assigned to each Deep Q-Network and dividing the total portfolio value into smaller parts. Furthermore, this framework is flexible enough to handle an arbitrary number of assets.
🧞‍♂️🧞🧞‍♀️Time-driven feature-aware jointly deep reinforcement learning for financial signal representation and algorithmic trading [76]
🧞‍♂️🧞🧞‍♀️Suri, K.; Saurav, S. Attentive Hierarchical Reinforcement Learning for Stock Order Executions. Available online: [22]	6 stocks 2min, 2months	OHLCV  // 1 month unclear%	https://www.semanticscholar.org/paper/Attentive-Hierarchical-Reinforcement-Learning-for-Suri/d7b927de3799871e370886af07a9ff0eab56de99	https://github.com/karush17/Hierarchical-Attention-Reinforcement-Learning (accessed 5 October 2021).
Suri, K.; Shi, X.Q.; Plataniotis, K.; Lawryshyn, Y. TradeR: Practical Deep Hierarchical Reinforcement Learning for Trade Execution.arXiv 2021, arXiv:2104.00620. [72]	35 stocks 1 min, 1 year	OHLCV   //  unclear