{"paper_id":"2407.01577","title":"MOT: A Mixture of Actors Reinforcement Learning Method by Optimal Transport for Algorithmic Trading","authors":["Xi Cheng","Jinghao Zhang","Yunan Zeng","Wenfang Xue"],"paper_date":"2024-06-03","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2407.01577v1","page_url":"https://thequant.space/flowcharts/mot-a-mixture-of-actors-reinforcement-learning-method-by-op/","scores":{"empirical_rigor":6.5,"math_complexity":7.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes MOT, a reinforcement‑learning model with multiple actors, disentangled representation learning, an Optimal Transport allocation module, and a pre‑training module for imitation learning.","quote":"In this paper, we propose MOT, which designs multiple actors with disentangled representation learning to model the different patterns of the market.","summary":"Algorithmic trading refers to executing buy and sell orders for specific assets based on automatically identified trading opportunities. Strategies based on reinforcement learning (RL) have demonstrated remarkable capabilities in addressing algorithmic trading problems. However, the trading…","strategy":"MOT"},"assumptions":{"status":"available","items":[{"assumption":"The actions of individual traders do not affect the overall asset price in the market.","type":"market","stated":"explicit","quote":"We assume that the actions of individual traders do not affect the overall asset price in the market."},{"assumption":"Transaction fee rate and slippage are fixed constants (µ and σ) used in reward calculation.","type":"execution","stated":"explicit","quote":"We set transaction fee rate µ = 2.3 × 10^5 and slippage σ = 0.2."}]},"datasets":{"status":"available","items":[{"name":"IF stock index futures dataset","provider":"ricequant.com","kind":"market-prices","access":"public","period":"training 2015-12-31 to 2018-05-08, test ","universe":null,"quote":"we collected it from ricequant.com5, and divided the data into a training set from 2015-12-31 to 2018-05-08 and a test set from 2018-05-09 to 2019-05-09.","known_id":"ricequant"}],"known":[{"id":"ricequant","name":"RiceQuant","provider":"RiceQuant","kind":"market-prices","access":"commercial","quote":"We collected it from ricequant.com5, and divided the data into a training set from 2015-12-31 to 2018-05-08 and a test set from 2018-05-09 to 2019-05-09.","mentions":2,"used_in":1}],"sample":{"start":null,"end":null,"market":null,"asset_class":"futures","frequency":null},"data_resolution":"intraday-bars"},"transaction_costs":{"status":"available","modeled":"yes","headline_net_of_costs":true,"detail":"Transaction fee rate µ = 2.3 × 10^5 and slippage σ = 0.2 are incorporated into the reward function.","quote":"We set transaction fee rate µ = 2.3 × 10^5 and slippage σ = 0.2.","source":"front_matter","rule":"R3","candidates":{"front_matter":"yes","evidence_card":"yes","evidence_card_quoted":true},"card_detail":"Transaction fee rate µ = 2.3 × 10^5 and slippage σ = 0.2 are incorporated into the reward function.","card_quote":"We set transaction fee rate µ = 2.3 × 10^5 and slippage σ = 0.2.","meaning":"costs are part of the reported headline results"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"MOT achieves the highest accumulated rate of return (ARR) among all baselines, with ARR 20.379, and shows superior risk‑reward balance.","kind":"performance","quote":"From Table 2, MOT outperforms other methods in terms of profit and risk-reward balance. ARR is the most crucial indicator, and our model achieves the highest ARR."},{"finding":"In ablation studies, MOT performs best in terms of ARR, volatility, annualized Sharpe ratio, and Sortino ratio, confirming the contribution of its three components.","kind":"performance","quote":"Table 2 shows that MOT performs best in terms of ARR, VO, ASR, and SOR."}],"reported_performance":{"strategy":"MOT","sharpe":null,"sharpe_benchmark":null,"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":11,"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":"2026-11-14T18:08:12Z"},"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/"}