{"paper_id":"2412.18563","title":"A Deep Reinforcement Learning Framework for Dynamic Portfolio Optimization: Evidence from China's Stock Market","authors":["Gang Huang","Xiaohua Zhou","Qingyang Song"],"paper_date":"2024-12-24","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2412.18563v3","page_url":"https://thequant.space/flowcharts/a-deep-reinforcement-learning-framework-for-dynamic-portfoli/","scores":{"empirical_rigor":8,"math_complexity":7,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes a novel Sharpe ratio reward function for Actor-Critic DRL algorithms and a comprehensive DRL methodology integrating VGG-based networks and random sampling for dynamic portfolio optimization.","quote":"First, we introduce a novel Sharpe ratio reward function specifically designed for Actor-Critic DRL algorithms, achieving stable convergence during training and consistently positive Sharpe ratios in practice.","summary":"Artificial intelligence is transforming financial investment decision-making frameworks, with deep reinforcement learning demonstrating substantial potential in robo-advisory applications. This paper addresses the limitations of traditional portfolio optimization methods in dynamic asset weight…","strategy":"Deep Reinforcement Learning (DRL) portfolio optimization"},"assumptions":{"status":"available","items":[{"assumption":"Short‑selling is prohibited, i.e., only long‑only positions are allowed.","type":"market","stated":"explicit","quote":"Under short-selling restrictions (long-only positions), the reward function in current DRL portfolio weight optimization models primarily consists of portfolio returns"},{"assumption":"Only one transaction per stock per day is allowed.","type":"execution","stated":"explicit","quote":"The study restricts trading to one transaction per stock per day."},{"assumption":"All price data are forward‑adjusted daily records from the Wind database.","type":"data","stated":"explicit","quote":"The data is obtained from the Wind database's daily trading records, with all prices forward-adjusted."},{"assumption":"The portfolio contains one risk‑free asset (cash) and ten risky assets.","type":"model","stated":"explicit","quote":"The portfolio consists of 1 risk-free asset (cash) and 10 risky assets."},{"assumption":"Backtesting uses exclusively out‑of‑sample data that were not seen during training.","type":"execution","stated":"explicit","quote":"The backtesting period encompasses exclusively out-of-sample data, independent from the training dataset."},{"assumption":"Randomly selected constituent stocks from the CSI 300 index represent a generic portfolio for testing DRL adaptability.","type":"other","stated":"implied","quote":"This study constructs an investment portfolio using randomly selected constituent stocks from the CSI300 index for empirical analysis."}]},"datasets":{"status":"available","items":[{"name":"CSI300 constituent stocks (random selection)","provider":"Wind","kind":"market-prices","access":"commercial","period":"Training: 03/17/2010 - 08/02/2023; Testi","universe":"Randomly selected constituent stocks from the CSI 300 Index","quote":"This study constructs an investment portfolio using randomly selected constituent stocks from the CSI300 index for empirical analysis. The portfolio consists of 1 risk-free asset (cash) and 10 risky assets. The data is obtained from the Wind database's daily trading records"}],"known":[{"id":"wind","name":"Wind","provider":"Wind Information","kind":"market-prices","access":"commercial","quote":"The data is obtained from the Wind database's daily trading records, with all prices forward-adjusted.","mentions":1,"used_in":1}],"sample":{"start":"2023-08","end":"2024-02","market":"CSI 300 constituent stocks","asset_class":"equities","frequency":"daily"},"data_resolution":"daily"},"transaction_costs":{"status":"available","modeled":"yes","headline_net_of_costs":true,"detail":"Initial allocation incurred ~0.22% cost; subsequent daily costs ranged between 0.002% and 0.01% on most trading days.","quote":"Substantial transaction costs (approximately 0.22%) were incurred solely during initial capital allocation, with subsequent transaction cost rates maintaining minimal levels between 0.002% and 0.01% on most trading days.","source":"front_matter","rule":"R3","candidates":{"front_matter":"yes","evidence_card":"yes","evidence_card_quoted":true},"card_detail":"Initial allocation incurred ~0.22% cost; subsequent daily costs ranged between 0.002% and 0.01% on most trading days.","card_quote":"Substantial transaction costs (approximately 0.22%) were incurred solely during initial capital allocation, with subsequent transaction cost rates maintaining minimal levels between 0.002% and 0.01% on most trading days.","meaning":"costs are part of the reported headline results"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"The DRL model achieved the highest annualized average return of 19.56%, a Sharpe ratio of 1.5550, Sortino ratio of 2.9567, maximum drawdown of 5.85% and Calmar ratio of 3.3395, outperforming all benchmark models.","kind":"performance","quote":"The model achieved the highest annualized average return of 19.56%, maintained moderate volatility (12.58%), and notably outperformed other models with a Sharpe ratio of 1.5550"},{"finding":"Weight adjustments remained stable (standard deviation 0.031‑0.033) with cash holdings between 0.11 and 0.12, indicating effective diversification and liquidity management.","kind":"performance","quote":"weight standard deviation stabilizing between 0.031 and 0.033, demonstrating effective diversification characteristics. The cash position fluctuated within a narrow range of 0.11 to 0.12, ensuring adequate portfolio liquidity."}],"reported_performance":{"strategy":"Deep Reinforcement Learning (DRL) portfolio optimization","sharpe":1.555,"sharpe_benchmark":null,"annual_return_pct":19.56,"total_return_pct":12.56,"max_drawdown_pct":5.85},"out_of_sample":{"method":"holdout","headline_out_of_sample":true}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":26,"citations":{"cited_by_in_corpus":2,"by_independent_authors":2,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":1,"unclassified":1},"independent_papers":[],"scope":"Citations between papers in this corpus only; citations from outside it are not counted."}},"implementation":{"status":"available","public":false,"code_url":null,"note":"No repository presented by the authors as their own was found in the paper. Absence here is not proof that no code exists."},"replication":{"status":"none_found","card":null,"note":"No replication of this paper has been run by thequant.space yet."},"extraction":{"text_source":"fulltext","model":"openai/gpt-oss-120b","version":1,"extracted_at":"2026-11-14T17:48:46Z"},"provenance":{"claims":"Everything here is what the authors state in the paper. Nothing was re-run or reproduced by the platform.","quotes":"Assumptions, datasets, cost detail and findings were extracted by a language model. Every quote is verbatim paper text. Where an item has `support`, \"full\" means every figure in it appears in the quoted sentences and \"partial\" means a figure is stated elsewhere in the paper; items with a figure found nowhere in the paper were discarded.","datasets_known":"datasets.known lists well-known vendors and public datasets by a stable id, found by a dictionary over the full text where the sentence says the data is used; it is independent of the model and covers only names in the dictionary.","flags":"transaction_costs.modeled, results.evaluation_type and results.out_of_sample.method are platform classifications (structured-decision models); see https://thequant.space/score-guide/#penalty-flags","comparisons":"supports / contradicts / qualifies are a language model's reading of two papers' quoted findings, restricted to closely related papers that share no author. They are pointers to read, not verified replications, and coverage is partial.","implementation":"code_url is a repository the paper itself presents as its own (rule-scored, ambiguous cases judged by a model), checked for liveness when it was recorded."},"docs":"https://thequant.space/agents/"}