{"paper_id":"2311.13326","title":"Curriculum Learning and Imitation Learning for Model-free Control on Financial Time-series","authors":["Woosung Koh","Insu Choi","Yuntae Jang","Gimin Kang","Woo Chang Kim"],"paper_date":"2023-11-22","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2311.13326v4","page_url":"https://thequant.space/flowcharts/curriculum-learning-and-imitation-learning-for-model-free-co/","scores":{"empirical_rigor":6,"math_complexity":6.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes applying curriculum learning via data augmentation and imitation learning via policy distillation from an oracle to improve control tasks on financial time-series.","quote":"We implement the fundamental ideas of curriculum learning via data augmentation, while imitation learning is implemented via policy distillation from an oracle.","summary":"Curriculum learning and imitation learning have been leveraged extensively in the robotics domain. However, minimal research has been done on leveraging these ideas on control tasks over highly stochastic time-series data. Here, we theoretically and empirically explore these approaches in a…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"The training data is a fixed sampled approximation to the data-generating process and cannot be further sampled without the passage of time.","type":"data","stated":"explicit","quote":"the training data ˆpdata, which is a sampled approximation to pdata, is fixed and can not be further sampled without the passage of time."},{"assumption":"Portfolio exposure is constrained: max aggregate gross exposure of 1 (net [-1,1]) for Data Set 1 and 2 (net [-2,2]) for Data Set 2.","type":"execution","stated":"explicit","quote":"Constraint 1 (Data Set 1): The portfolio’s maximum aggregate gross exposure is 1. Equivalently, the net exposure is bound by [-1, 1]. Constraint 2 (Data Set 2): The portfolio’s maximum aggregate gross exposure is 2. Equivalently, the net exposure is bound by [-2, 2]."},{"assumption":"All overlapping hyperparameters are tuned for the baseline algorithm, giving the baseline an advantage.","type":"model","stated":"explicit","quote":"These findings are especially encouraging as we tune all overlapping hyperparameters on the baseline -- giving an advantage to the baseline."}]},"datasets":{"status":"available","items":[{"name":"Data Set 1","provider":null,"kind":"macro","access":"unknown","period":null,"universe":null,"quote":"We hereforth refer to Data Sets 1 and 2 as representing the Macro ETFs and Commodity Futures environments in Table 1, respectively."},{"name":"Data Set 2","provider":null,"kind":"other","access":"unknown","period":null,"universe":null,"quote":"We hereforth refer to Data Sets 1 and 2 as representing the Macro ETFs and Commodity Futures environments in Table 1, respectively."}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"daily"},"transaction_costs":{"status":"available","modeled":"no","headline_net_of_costs":null,"detail":null,"quote":null,"source":"front_matter","rule":"R1","candidates":{"front_matter":"no","evidence_card":"unclear","evidence_card_quoted":false},"meaning":"a trading or execution result is reported without costs"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"Curriculum learning methods (EMA5, IS8, TIS) achieve the best performance across all empirical environments, with EMA5 attaining statistical significance (<0.05 p‑value) in all six cases.","kind":"performance","quote":"each best result is the EMA-based CL we propose—{EMA5, IS8, TIS}. Consistent with expectations, the naïve rounding approach’s performance significantly lags the EMA-based approaches."},{"finding":"Imitation learning approaches (A2C‑DPD, A2C‑DPD‑LGN, etc.) dramatically worsen performance, often failing to take any position and yielding near‑flat test‑set results.","kind":"negative","quote":"The most extreme case can be viewed in Figure 11 where A2C-DPD and A2C-DPD-LGN refuses to take any position at all, resulting in a nearly flat test set performance."}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":16,"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":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":"2026-11-14T18:18:57Z"},"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/"}