# The Bidding Games: Reinforcement Learning for MEV Extraction on Polygon Blockchain

arXiv: https://arxiv.org/abs/2510.14642 · HTML: https://mlsanity.com/paper/2510.14642/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Adversarial robustness and RL in finance, one of 15 directions in Deep reinforcement learning methods.
- Builds on 13 of its 60 references that are in the map.
- First posted on arXiv 16 Oct 2025.

## Placed in

- Deep reinforcement learning methods / [Adversarial robustness and RL in finance](https://mlsanity.com/deeprl/adversarial-robustness-and-rl-in-finance/)

## Builds on (most cited first, 13 of 13)

- [Real-Time Bidding by Reinforcement Learning in Display Advertising](https://mlsanity.com/paper/1701.02490/) (2017)
- [Real-Time Bidding with Multi-Agent Reinforcement Learning in Display Advertising](https://mlsanity.com/paper/1802.09756/) (2018)
- [Trajectory-wise Iterative Reinforcement Learning Framework for Auto-bidding](https://mlsanity.com/paper/2402.15102/) (2024)
- [Learning to Play Against Unknown Opponents](https://mlsanity.com/paper/2412.18297/) (2024)
- [Shill-Proof Auctions](https://mlsanity.com/paper/2404.00475/) (2024)
- [Prior-Independent Bidding Strategies for First-Price Auctions](https://mlsanity.com/paper/2502.09907/) (2025)
- [User Response in Ad Auctions: An MDP Formulation of Long-Term Revenue Optimization](https://mlsanity.com/paper/2302.08108/) (2023)
- [Strategic Bidding Wars in On-chain Auctions](https://mlsanity.com/paper/2312.14510/) (2023)
- [Who Wins Ethereum Block Building Auctions and Why?](https://mlsanity.com/paper/2407.13931/) (2024)
- [On the Welfare of EIP-1559 with Patient Bidders](https://mlsanity.com/paper/2502.20031/) (2025)
- [Transaction Fee Mechanism Design for Leaderless Blockchain Protocols](https://mlsanity.com/paper/2505.17885/) (2025)
- [Equilibrium Computation in First-Price Auctions with Correlated Priors](https://mlsanity.com/paper/2506.05322/) (2025)
- [Unpacking Maximum Extractable Value on Polygon: A Study on Atomic Arbitrage](https://mlsanity.com/paper/2508.21473/) (2025)

## Abstract (arXiv)

In blockchain networks, the strategic ordering of transactions within blocks has emerged as a significant source of profit extraction, known as Maximal Extractable Value (MEV). The transition from spam-based Priority Gas Auctions (PGA) to structured auction mechanisms like Polygon Atlas has transformed MEV extraction from public bidding wars into sealed-bid competitions under extreme time constraints. While this shift reduces network congestion, it introduces complex strategic challenges where searchers must make optimal bidding decisions within a sub-second window without knowledge of competitor behavior or presence. Traditional equilibrium-based game-theoretic models struggle in this high-frequency, partially observable environment. While auction theory provides equilibrium solutions for sealed-bid formats under incomplete information, these models typically assume known bidder value distributions and stationary competition--assumptions that are difficult to satisfy in dynamic, sub-second auctions where competitor presence and strategies evolve rapidly. We present a reinforcement learning framework for MEV extraction on Polygon Atlas and make three contributions: (1) A novel simulation environment that accurately models the stochastic arrival of arbitrage opportunities and probabilistic competition in Atlas auctions; (2) A PPO-based bidding agent optimized for real-time constraints, capable of adaptive strategy formulation in continuous action spaces while maintaining production-ready inference speeds; (3) Empirical validation demonstrating our history-conditioned agent achieves 49% Maximum-Profit Capture when deployed alongside existing searchers and a 43% relative profit improvement over the historical market leader in counterfactual replacement, significantly outperforming static bidding strategies.