用强化学习优化做市商的流动性分配，降低极端亏损风险。
Concentrated Liquidity Provision: a Reinforcement Learning Perspective
- 将做市决策建模为随机脉冲控制问题，用强化学习求解。
- 学习到的策略能根据价格错配、成本和风险偏好动态调仓。
- 相比传统方法，显著压缩了盈亏分布的左尾，抗风险更强。
自动化做市商（AMM）是去中心化金融（DeFi）的核心。像UniswapV3这样的恒定乘积市场采用集中流动性设计，已成为主流。在此类市场中，做市商（LPs）面临一个序列决策问题：需决定何时调整仓位及在哪些价格区间分配资本，以应对市场变化。本文将动态流动性提供建模为随机脉冲控制问题，并使用强化学习（RL）求解，重点在于获得可解释的策略。我们发现，所学策略展现出丰富的状态依赖行为，能根据价格错配、再平衡成本、不确定性、头寸暴露及异质风险偏好进行流动性分配。这些行为有助于压缩盈利亏损（PnL）分布的左尾，在高不确定性下避免灾难性损失。最后，我们将RL代理与基准及文献中先进的代理进行对比，并分析其性能表现。
原文摘要 · Abstract (English)
Automated market makers (AMMs) are a cornerstone of decentralised finance (DeFi). Constant product markets with concentrated liquidity, such as UniswapV3, are now a well-established design. In these markets, liquidity providers (LPs) face a sequential decision problem: they must decide when to rebalance their positions and which price ranges to allocate capital to as market conditions evolve. We formulate dynamic liquidity provision as a stochastic impulse control problem and use reinforcement learning (RL) to solve it, focusing on providing interpretable solutions. We show that learned policies exhibit rich state-dependent behaviour, allocating liquidity according to mispricing, rebalancing costs, uncertainty, inventory exposure, and heterogeneous risk preferences. These behaviours help compress the left tail of the Profit and Loss (PnL) distribution and avoid catastrophic outcomes under high uncertainty. Finally, we benchmark the RL agents against baseline and sophisticated agents from the AMM microstructure literature and analyse their performance.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。