Adaptive Dueling Double Deep Q-networks in Uniswap V3 Replication and Extension with Mamba

TL;DR

This paper replicates and enhances a deep reinforcement learning model for Uniswap V3 liquidity provision by integrating Mamba with DDQN and introducing new data handling and reward strategies, resulting in improved performance and theoretical robustness.

Contribution

It introduces a novel structure combining Mamba with DDQN and a new reward function, improving upon the original model for Uniswap V3 liquidity provision.

Findings

Model shows stronger theoretical support than original.

Performs better in some test scenarios.

Includes new baselines and data cleaning methods.

Abstract

The report goes through the main steps of replicating and improving the article "Adaptive Liquidity Provision in Uniswap V3 with Deep Reinforcement Learning." The replication part includes how to obtain data from the Uniswap Subgraph, details of the implementation, and comments on the results. After the replication, I propose a new structure based on the original model, which combines Mamba with DDQN and a new reward function. In this new structure, I clean the data again and introduce two new baselines for comparison. As a result, although the model has not yet been applied to all datasets, it shows stronger theoretical support than the original model and performs better in some tests.