集中流动性提供：强化学习视角
Concentrated Liquidity Provision: a Reinforcement Learning Perspective
浏览论文内容
中文总结 AI 辅助
该研究将DeFi中集中流动性提供建模为随机脉冲控制问题，采用强化学习求解，其策略可压缩损益分布左尾、规避高不确定性下的灾难性结果，且性能优于AMM微观结构文献中的相关基准与复杂智能体。
中文摘要 AI 辅助
自动做市商（AMMs）是去中心化金融（DeFi）的基石，UniswapV3等采用集中流动性的恒定乘积市场现已成为成熟设计。在这类市场中，流动性提供者（LPs）面临序列决策问题：需随市场变化决定何时再平衡头寸、将资本分配至哪些价格区间。我们将动态流动性提供建模为随机脉冲控制问题，并采用强化学习（RL）求解，重点提供可解释的解决方案。研究表明，学习得到的策略展现出丰富的状态依赖行为，会根据定价偏差、再平衡成本、不确定性、库存敞口及异质风险偏好分配流动性；这些行为有助于压缩损益（PnL）分布的左尾，在高不确定性下避免灾难性结果。最后，我们将RL智能体与AMM微观结构文献中的基准智能体及复杂智能体进行对比，分析其性能。
英文摘要
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.
发表机构
- University of Liverpool（利物浦大学）
- University of Oxford（牛津大学）
机构由 AI 辅助整理，请以论文原文为准。
