MOT: A Mixture of Actors Reinforcement Learning Method by Optimal Transport for Algorithmic Trading
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910509835485184 |
|---|---|
| author | Cheng, Xi Zhang, Jinghao Zeng, Yunan Xue, Wenfang |
| author_facet | Cheng, Xi Zhang, Jinghao Zeng, Yunan Xue, Wenfang |
| contents | 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 patterns differ among market conditions due to shifted distribution data. Ignoring multiple patterns in the data will undermine the performance of RL. In this paper, we propose MOT,which designs multiple actors with disentangled representation learning to model the different patterns of the market. Furthermore, we incorporate the Optimal Transport (OT) algorithm to allocate samples to the appropriate actor by introducing a regularization loss term. Additionally, we propose Pretrain Module to facilitate imitation learning by aligning the outputs of actors with expert strategy and better balance the exploration and exploitation of RL. Experimental results on real futures market data demonstrate that MOT exhibits excellent profit capabilities while balancing risks. Ablation studies validate the effectiveness of the components of MOT. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_01577 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MOT: A Mixture of Actors Reinforcement Learning Method by Optimal Transport for Algorithmic Trading Cheng, Xi Zhang, Jinghao Zeng, Yunan Xue, Wenfang Trading and Market Microstructure Artificial Intelligence Machine Learning 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 patterns differ among market conditions due to shifted distribution data. Ignoring multiple patterns in the data will undermine the performance of RL. In this paper, we propose MOT,which designs multiple actors with disentangled representation learning to model the different patterns of the market. Furthermore, we incorporate the Optimal Transport (OT) algorithm to allocate samples to the appropriate actor by introducing a regularization loss term. Additionally, we propose Pretrain Module to facilitate imitation learning by aligning the outputs of actors with expert strategy and better balance the exploration and exploitation of RL. Experimental results on real futures market data demonstrate that MOT exhibits excellent profit capabilities while balancing risks. Ablation studies validate the effectiveness of the components of MOT. |
| title | MOT: A Mixture of Actors Reinforcement Learning Method by Optimal Transport for Algorithmic Trading |
| topic | Trading and Market Microstructure Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2407.01577 |