A PPO-trained agent that dynamically adjusts Uniswap v3 liquidity ranges beat a fixed 500-hour periodic rebalancing heuristic in 7 of 11 out-of-sample windows on WETH/USDC.
In NeurIPS 2023 Workshop on Instruction Tuning and Instruction F ol- lowing
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
q-fin.CP 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Improving DeFi Accessibility through Efficient Liquidity Provisioning with Deep Reinforcement Learning
A PPO-trained agent that dynamically adjusts Uniswap v3 liquidity ranges beat a fixed 500-hour periodic rebalancing heuristic in 7 of 11 out-of-sample windows on WETH/USDC.