{"paper_id":"2406.08013","title":"Deep reinforcement learning with positional context for intraday trading","authors":["Sven Goluža","Tomislav Kovačević","Tessa Bauman","Zvonko Kostanjčar"],"paper_date":"2024-06-12","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2406.08013v1","page_url":"https://thequant.space/flowcharts/deep-reinforcement-learning-with-positional-context-for-intr/","scores":{"empirical_rigor":8,"math_complexity":7.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes a novel deep reinforcement learning model for intraday trading that incorporates positional features into a sparse state space.","quote":"This paper introduces three contributions. Primarily, we present a novel DRL model for intraday trading strategies, which integrates positional features as a pivotal component.","summary":"Deep reinforcement learning (DRL) is a well-suited approach to financial decision-making, where an agent makes decisions based on its trading strategy developed from market observations. Existing DRL intraday trading strategies mainly use price-based features to construct the state space. They…","strategy":"Deep reinforcement learning (DRL) intraday trading model"},"assumptions":{"status":"available","items":[{"assumption":"Transaction costs consist of commission, slippage, and negligible market impact.","type":"execution","stated":"explicit","quote":"The transaction costs txt include commission, slippage, and market impact. Commission cost estimates (COM) are expressed in basis points (BP)"},{"assumption":"Commission is measured in basis points (1BP = 0.01%).","type":"model","stated":"explicit","quote":"Commission cost estimates (COM) are expressed in basis points (BP), where 1BP equals 0.01%."},{"assumption":"Trades are executed at the next period's open price for slippage estimation.","type":"execution","stated":"explicit","quote":"Slippage is conservatively approximated by assuming that trades execute at the Open price pO t+1 of the next time step"},{"assumption":"The action space represents the position to hold, not direct buy/sell orders.","type":"model","stated":"explicit","quote":"This action space also represents the position the agent needs to take in the asset, not the actual trading decisions of buying or selling the asset"},{"assumption":"Reward is additive logarithmic return at each time step.","type":"statistical","stated":"explicit","quote":"To satisfy the additive rewards required by the DRL optimization goal, we define the reward function as the logarithmic return at each time step"}]},"datasets":{"status":"available","items":[{"name":"Private market data","provider":"private data vendor","kind":"market-prices","access":"commercial","period":"nearly a decade","universe":"commodities and foreign exchange securities","quote":"It is evaluated across various assets, including commodities and foreign exchange securities, over an extensive evaluation period of nearly a decade."},{"name":"Data from FirstRateData","provider":"FirstRateData","kind":"market-prices","access":"commercial","period":null,"universe":null,"quote":"Data is provided by a private data vendor at https://firstratedata.com."}],"known":[],"sample":{"start":"2013","end":"2022","market":"commodities and foreign exchange","asset_class":"multi-asset","frequency":"intraday"},"data_resolution":"intraday-bars"},"transaction_costs":{"status":"available","modeled":"yes","headline_net_of_costs":true,"detail":"Commission expressed in basis points, slippage assumed at next open price, market impact considered negligible for one-unit trades.","quote":"The transaction costs txt include commission, slippage, and market impact. Commission cost estimates (COM) are expressed in basis points (BP)","source":"front_matter","rule":"R3","candidates":{"front_matter":"yes","evidence_card":"yes","evidence_card_quoted":true},"card_detail":"Commission expressed in basis points, slippage assumed at next open price, market impact considered negligible for one-unit trades.","card_quote":"The transaction costs txt include commission, slippage, and market impact. Commission cost estimates (COM) are expressed in basis points (BP)","meaning":"costs are part of the reported headline results"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"The DRL agent outperforms benchmark strategies in most assets, delivering high Sharpe ratios after accounting for realistic transaction costs.","kind":"performance","quote":"Our DRL agent demonstrates notable performance, outperforming the benchmarks in most assets and yielding high Sharpe ratios after accounting for realistic transaction costs."},{"finding":"Models with positional features achieve higher Sharpe ratios than those without, especially under higher commission fees.","kind":"performance","quote":"Our findings indicate that, on average, the model with positional features outperforms the alternative across higher commission fees."},{"finding":"The agent concentrates trades early in the day and reduces activity later, suggesting learned avoidance of higher volatility near market close.","kind":"other","quote":"The agent initiates the majority of trades early in the day, gradually reducing its trading activity as the day progresses toward its conclusion."}],"reported_performance":{"strategy":"Deep reinforcement learning (DRL) intraday trading model","sharpe":3.812,"sharpe_benchmark":-0.156,"annual_return_pct":null,"total_return_pct":null,"max_drawdown_pct":null},"out_of_sample":{"method":"holdout","headline_out_of_sample":true}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":27,"citations":{"cited_by_in_corpus":1,"by_independent_authors":0,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"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":"2026-11-14T16:35:57Z"},"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/"}