DeepSeekMath Meets Order Book: Group-Aware Policy Optimization for High-Frequency Directional Trading
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918521146966016 |
|---|---|
| author | Charabarty, Sayak Pal, Souradip |
| author_facet | Charabarty, Sayak Pal, Souradip |
| contents | This paper studies reinforcement learning for high-frequency trading on limit order books by pairing an Order-Flow-based state model with policy-gradient methods. Instead of value-based RL techniques like tabular Q-learning, our approach deploys policy-based methods like vanilla PPO and DeepSeekMath-inspired variants like GRPO and GSPO, that use group-normalized updates and downside-aware shaping. On backtests with financial assets AMZN, AAPL, and GOOG under a simplified backtesting setup based on spread-scaled rewards, these new policies improve net average PnL, profitability, and drawdown over the Q-Learning baseline. Our results show that (1) Order-Flow signals are an adequate state for policy RL and (2) group-aware PPO surrogates are preferable over value-based baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_25527 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | DeepSeekMath Meets Order Book: Group-Aware Policy Optimization for High-Frequency Directional Trading Charabarty, Sayak Pal, Souradip Machine Learning Computational Engineering, Finance, and Science I.2.m This paper studies reinforcement learning for high-frequency trading on limit order books by pairing an Order-Flow-based state model with policy-gradient methods. Instead of value-based RL techniques like tabular Q-learning, our approach deploys policy-based methods like vanilla PPO and DeepSeekMath-inspired variants like GRPO and GSPO, that use group-normalized updates and downside-aware shaping. On backtests with financial assets AMZN, AAPL, and GOOG under a simplified backtesting setup based on spread-scaled rewards, these new policies improve net average PnL, profitability, and drawdown over the Q-Learning baseline. Our results show that (1) Order-Flow signals are an adequate state for policy RL and (2) group-aware PPO surrogates are preferable over value-based baselines. |
| title | DeepSeekMath Meets Order Book: Group-Aware Policy Optimization for High-Frequency Directional Trading |
| topic | Machine Learning Computational Engineering, Finance, and Science I.2.m |
| url | https://arxiv.org/abs/2605.25527 |