Meta-Learning Reinforcement Learning for Crypto-Return Prediction
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910007093624832 |
|---|---|
| author | Wang, Junqiao Guan, Zhaoyang Liu, Guanyu Xia, Tianze Li, Xianzhi Yin, Shuo Song, Xinyuan Cheng, Chuhan Shi, Tianyu Lee, Alex |
| author_facet | Wang, Junqiao Guan, Zhaoyang Liu, Guanyu Xia, Tianze Li, Xianzhi Yin, Shuo Song, Xinyuan Cheng, Chuhan Shi, Tianyu Lee, Alex |
| contents | Predicting cryptocurrency returns is notoriously difficult: price movements are driven by a fast-shifting blend of on-chain activity, news flow, and social sentiment, while labeled training data are scarce and expensive. In this paper, we present Meta-RL-Crypto, a unified transformer-based architecture that unifies meta-learning and reinforcement learning (RL) to create a fully self-improving trading agent. Starting from a vanilla instruction-tuned LLM, the agent iteratively alternates between three roles-actor, judge, and meta-judge-in a closed-loop architecture. This learning process requires no additional human supervision. It can leverage multimodal market inputs and internal preference feedback. The agent in the system continuously refines both the trading policy and evaluation criteria. Experiments across diverse market regimes demonstrate that Meta-RL-Crypto shows good performance on the technical indicators of the real market and outperforming other LLM-based baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_09751 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Meta-Learning Reinforcement Learning for Crypto-Return Prediction Wang, Junqiao Guan, Zhaoyang Liu, Guanyu Xia, Tianze Li, Xianzhi Yin, Shuo Song, Xinyuan Cheng, Chuhan Shi, Tianyu Lee, Alex Machine Learning Artificial Intelligence Predicting cryptocurrency returns is notoriously difficult: price movements are driven by a fast-shifting blend of on-chain activity, news flow, and social sentiment, while labeled training data are scarce and expensive. In this paper, we present Meta-RL-Crypto, a unified transformer-based architecture that unifies meta-learning and reinforcement learning (RL) to create a fully self-improving trading agent. Starting from a vanilla instruction-tuned LLM, the agent iteratively alternates between three roles-actor, judge, and meta-judge-in a closed-loop architecture. This learning process requires no additional human supervision. It can leverage multimodal market inputs and internal preference feedback. The agent in the system continuously refines both the trading policy and evaluation criteria. Experiments across diverse market regimes demonstrate that Meta-RL-Crypto shows good performance on the technical indicators of the real market and outperforming other LLM-based baselines. |
| title | Meta-Learning Reinforcement Learning for Crypto-Return Prediction |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2509.09751 |