{"paper_id":"2610.01325","title":"PPO-HRAP: Proximal Policy Optimization with a Hybrid Regime-Aware Policy for Risk-Controlled Trading","authors":["Duong Hien Chi Kien","Thanh Trung Huynh"],"paper_date":"2026-10-01","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2610.01325","page_url":"https://thequant.space/flowcharts/ppo-hrap-proximal-policy-optimization-with-a-hybrid-regime-aware-policy-for/","scores":{"empirical_rigor":7,"math_complexity":6,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes PPO-HRAP, a hybrid regime-aware policy that combines Proximal Policy Optimization with an interpretable regime prior.","quote":"This paper proposes PPO-HRAP, a hybrid regime-aware policy that combines Proximal Policy Optimization with an interpretable regime prior.","summary":"Reinforcement learning for trading often struggles to balance upside participation with drawdown control. Profit-only policies can collapse toward passive long exposure on upward-drifting assets, while aggressively risk-penalized rewards can become too defensive during volatile periods. This paper…","strategy":"PPO-HRAP"},"assumptions":{"status":"available","items":[{"assumption":"All methods are evaluated with a 0.1% proportional transaction cost.","type":"execution","stated":"implied","quote":"All methods use a 0.1% proportional transaction cost."},{"assumption":"Data are split chronologically: 2010–2017 for training, 2018–2019 for validation, and 2020–2022 for testing.","type":"data","stated":"implied","quote":"We use chronological splits: 2010–2017 for training, 2018–2019 for validation, and 2020–2022 for testing."},{"assumption":"The VIX z‑score is used to scale the dynamic drawdown penalty.","type":"market","stated":"implied","quote":"Thus, when VIX z-score rises, the drawdown penalty increases; when stress is low, the penalty relaxes toward its base level."},{"assumption":"The main SPY result uses random seed 42.","type":"model","stated":"implied","quote":"The main SPY result uses seed 42"},{"assumption":"Action‑prior weight ρ is set to 0.6 based on validation.","type":"model","stated":"implied","quote":"The validation search over ρ selects ρ= 0.6, with validation Calmar 0.2299 and validation total return 0.0800."}]},"datasets":{"status":"available","items":[{"name":"SPY","provider":null,"kind":"market-prices","access":"public","period":"2020–2022 (test), 2010–2017 (train), 201","universe":null,"quote":"On the held-out 2020–2022 SPY test window, PPO-HRAP achieves 27.62% total return..."},{"name":"QQQ","provider":null,"kind":"market-prices","access":"public","period":null,"universe":null,"quote":"Single-run cross-asset tests on QQQ and DIA further show that the proposed method ranks first on total return and Sharpe ratio for all three reported assets."},{"name":"DIA","provider":null,"kind":"market-prices","access":"public","period":null,"universe":null,"quote":"Single-run cross-asset tests on QQQ and DIA further show that the proposed method ranks first on total return and Sharpe ratio for all three reported assets."}],"known":[],"sample":{"start":"2020","end":"2022","market":"SPY (S&P 500 ETF)","asset_class":"equities","frequency":"daily"},"data_resolution":"daily"},"transaction_costs":{"status":"available","modeled":"yes","headline_net_of_costs":null,"detail":"0.1% proportional transaction cost applied to all methods","quote":"All methods use a 0.1% proportional transaction cost.","source":"evidence_card","rule":"R2","candidates":{"front_matter":"unclear","evidence_card":"yes","evidence_card_quoted":true},"card_detail":"0.1% proportional transaction cost applied to all methods","card_quote":"All methods use a 0.1% proportional transaction cost.","meaning":"costs are part of the reported headline results"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"PPO-HRAP achieves 27.62% total return, 8.48% annualized return, 0.6447 Sharpe, 0.8588 Sortino, 0.4592 Calmar, and reduces maximum drawdown from 34.10% (Buy and Hold) to 18.47% on SPY 2020–2022.","kind":"performance","quote":"PPO-HRAP achieves 27.62% total return, 8.48% annualized return, 0.6447 Sharpe ratio, 0.8588 Sortino ratio, and 0.4592 Calmar ratio, while reducing maximum drawdown from 34.10% for Buy and Hold to 18.47%."},{"finding":"Across five SPY seeds, PPO-HRAP shows mean total return $0.2725 \\pm 0.0109$ and mean Sharpe $0.6219 \\pm 0.0565$, indicating stability.","kind":"performance","quote":"Across five SPY seeds, PPO-HRAP remains stable with mean total return $0.2725 \\pm 0.0109$ and mean Sharpe ratio $0.6219 \\pm 0.0565$."},{"finding":"PPO-HRAP ranks first on total return and Sharpe ratio for SPY, QQQ, and DIA in single-run cross‑asset tests.","kind":"performance","quote":"PPO-HRAP ranks first on total return and Sharpe ratio for SPY, QQQ, and DIA."},{"finding":"Action‑prior weight ρ=0.6 yields validation Calmar 0.2299 and validation total return 0.0800; performance is non‑monotonic in ρ.","kind":"other","quote":"The validation search over ρ selects ρ= 0.6, with validation Calmar 0.2299 and validation total return 0.0800."},{"finding":"The smallest drawdown (9.51%) is achieved by PPO Static MDD but with much lower total return (5.91%).","kind":"performance","quote":"The smallest drawdown is obtained by PPO Static MDD (9.51%), but at the cost of a much lower total return (5.91%)."}],"reported_performance":{"strategy":"PPO-HRAP","sharpe":0.6447,"sharpe_benchmark":0.342,"annual_return_pct":8.48,"total_return_pct":27.62,"max_drawdown_pct":18.47},"out_of_sample":{"method":"holdout","headline_out_of_sample":true}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":43,"citations":{"cited_by_in_corpus":0,"by_independent_authors":0,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":0},"independent_papers":[],"scope":"Citations between papers in this corpus only; citations from outside it are not counted."}},"implementation":{"status":"available","public":true,"code_url":"https://github.com/chikien07012006/PPO_Regime-Aware-Trading","note":null},"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":"2026-11-14T16:29:01Z"},"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/"}