Papers › Select and Trade: Towards Unified Pair Trading with Hierarchical Reinforcement Learning

Select and Trade: Towards Unified Pair Trading with Hierarchical Reinforcement Learning

25 Jan 2023arXiv:2301.10724archive 2025-07-28

Weiguang Han, Boyi Zhang, Qianqian Xie, Min Peng, Yanzhao Lai, Jimin Huang

Pair trading is one of the most effective statistical arbitrage strategies which seeks a neutral profit by hedging a pair of selected assets. Existing methods generally decompose the task into two separate steps: pair selection and trading. However, the decoupling of two closely related subtasks can block information propagation and lead to limited overall performance. For pair selection, ignoring the trading performance results in the wrong assets being selected with irrelevant price movements, while the agent trained for trading can overfit to the selected assets without any historical information of other assets. To address it, in this paper, we propose a paradigm for automatic pair trading as a unified task rather than a two-step pipeline. We design a hierarchical reinforcement learning framework to jointly learn and optimize two subtasks. A high-level policy would select two assets from all possible combinations and a low-level policy would then perform a series of trading actions. Experimental results on real-world stock data demonstrate the effectiveness of our method on pair trading compared with both existing pair selection and trading methods.

PaperPDFCode

Code

chancefocus/trials officialmentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Hierarchical Reinforcement LearningPAIR TRADINGReinforcement Learning (RL)reinforcement-learning

Datasets

Introduced by this paper, per the archive.

CSI 300 Pair TradingS&P 500 Pair Trading

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
PAIR TRADING CSI 300 Pair Trading Trials Annual Return 0.68±0.51 #1 of 1 Archive leaderboard report
PAIR TRADING CSI 300 Pair Trading Trials Annual Volatility 0.26±0.09 #1 of 1 Archive leaderboard report
PAIR TRADING CSI 300 Pair Trading Trials Euclidean Distance 0.046±0.02 #1 of 1 Archive leaderboard report
PAIR TRADING CSI 300 Pair Trading Trials Max Dropdown -0.14±0.07 #1 of 1 Archive leaderboard report
PAIR TRADING CSI 300 Pair Trading Trials Sharpe Ratio 1.91±0.88 #1 of 1 Archive leaderboard report
PAIR TRADING S&P 500 Pair Trading Trials Annual Return 0.5±0.14 #1 of 1 Archive leaderboard report
PAIR TRADING S&P 500 Pair Trading Trials Annual Volatility 0.22±0.04 #1 of 1 Archive leaderboard report
PAIR TRADING S&P 500 Pair Trading Trials Euclidean Distance 0.037±0.01 #1 of 1 Archive leaderboard report
PAIR TRADING S&P 500 Pair Trading Trials Max Dropdown -0.09±0.01 #1 of 1 Archive leaderboard report
PAIR TRADING S&P 500 Pair Trading Trials Sharpe Ratio 1.84±0.24 #1 of 1 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections