Auto.gov: Learning-based Governance for Decentralized Finance (DeFi)

TL;DR

The paper addresses the vulnerability and inefficiency of traditional DeFi governance by introducing Auto.gov, a Deep Q-network-based governance agent that autonomously tunes protocol parameters in a stylized Aave-like lending environment. The approach treats parameter adjustment as a reinforcement learning control problem, demonstrating superior profitability and resilience to price oracle attacks compared with baselines and two benchmarks, including a real-world data evaluation. Key contributions include formalizing a tunable DeFi environment, integrating a learning-based governance agent, and showing rapid training and robust performance on attack scenarios. The results suggest that automated, data-driven governance can enhance security, profitability, and sustainability of DeFi protocols, with potential for broader applicability to other DeFi protocols and governance tasks.

Abstract

Decentralized finance (DeFi) is an integral component of the blockchain ecosystem, enabling a range of financial activities through smart-contract-based protocols. Traditional DeFi governance typically involves manual parameter adjustments by protocol teams or token holder votes, and is thus prone to human bias and financial risks, undermining the system's integrity and security. While existing efforts aim to establish more adaptive parameter adjustment schemes, there remains a need for a governance model that is both more efficient and resilient to significant market manipulations. In this paper, we introduce "Auto$.$gov", a learning-based governance framework that employs a deep Qnetwork (DQN) reinforcement learning (RL) strategy to perform semi-automated, data-driven parameter adjustments. We create a DeFi environment with an encoded action-state space akin to the Aave lending protocol for simulation and testing purposes, where Auto$.$gov has demonstrated the capability to retain funds that would have otherwise been lost to price oracle attacks. In tests with real-world data, Auto$.$gov outperforms the benchmark approaches by at least 14% and the static baseline model by tenfold, in terms of the preset performance metric--protocol profitability. Overall, the comprehensive evaluations confirm that Auto$.$gov is more efficient and effective than traditional governance methods, thereby enhancing the security, profitability, and ultimately, the sustainability of DeFi protocols.

Figures (15)

• Figure 1: A proposal in Aave governance forum to increase the liquidation threshold of the AAVE token depressedape.
• Figure 2: Action-state space encompassing users, lending pools and external markets of individual cryptocurrencies, and governance agent.
• Figure 3: Architecture of Auto.gov. The detailed defi environment is illustrated in \ref{['fig:arc-protocol']}.
• Figure 4: Operations for training the governance agent with the target network.
• Figure 5: Series of user reactions at each step (from "Start"-node to "Max step reached?"-node) of an episode under attack (\ref{['sec:attack-scenario']}), loan default (\ref{['sec:default']}), and ordinary (\ref{['sec:ordinary']}) scenarios, looping until episode ends ("End"-node).