---
title: Algorithmic Collusion by Reinforcement-Learning Pricing Agents: Simulation Evidence and Implications for Financial Markets and Competition Law
url: https://www.ml-quant.com/papers/ssrn/7500483/
site: ML-Quant (https://www.ml-quant.com)
updated: 2026-09-26
license: Summaries CC BY 4.0; links go to the original sources
index: https://www.ml-quant.com/llms.txt
identifier: SSRN 7500483
source_url: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7500483
featured: 2026-09-25
citations: unknown
topic: Trading, Microstructure & Execution
---


# Algorithmic Collusion by Reinforcement-Learning Pricing Agents: Simulation Evidence and Implications for Financial Markets and Competition Law

Q-learning pricing agents in simulated duopolies reach supracompetitive outcomes with no communication, achieving collusion indices of 0.778 and 40% profit gains over competitive benchmarks.

- Source: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7500483
- Identifier: SSRN 7500483
- Released: 2026-09-24
- First featured: Quant Letter No. 132 (2026-09-25): https://www.ml-quant.com/issues/2026-09-25/
- Citations (Semantic Scholar): not tracked
- Published in: not yet
- Topic: Trading, Microstructure & Execution
- Authors: Vladislav Dolgov

## Related

- [FAST: Efficient Action Tokenization for Vision-Language-Action Models](https://www.ml-quant.com/papers/arxiv/2501.09747/): A new tokenization scheme, Frequency-space Action Sequence Tokenization (FAST), has been proposed for robot actions, facilitating the training of vision-language action policies for complex and high-frequency tasks.
- [Deep Reinforcement Learning for Active High Frequency Trading](https://www.ml-quant.com/papers/arxiv/2101.07107/): A new Deep Reinforcement Learning framework has been developed for high frequency stock trading, showing potential for profitable long-term strategies.
- [TradeFM: A Generative Foundation Model for Trade-flow and Market Microstructure](https://www.ml-quant.com/papers/arxiv/2602.23784/): A Model for Trade-Flow in Market Microstructure: TradeFM is a new AI model that improves the analysis of market structures by studying billions of trade events in stocks, leading to better simulations of financial returns.
- [Romania's Roadmap to a Greener Financial System: An analysis of Environmental, Social and Governance Reporting on the Bucharest Exchange Trading Index](https://www.ml-quant.com/papers/ssrn/4440516/): Romania struggles to attract sustainable investments because its major companies have low transparency and high greenhouse gas emissions.
- [Robust insurance pricing and liquidity management](https://www.ml-quant.com/papers/arxiv/2510.15709/): Accounting for model uncertainty makes insurers set higher, more conservative prices and liquidity buffers, widens capacity ranges, and produces much longer underwriting cycles with more time in low‑capacity states.
- [A Microstructure Analysis of Coupling in CFMMs](https://www.ml-quant.com/papers/arxiv/2510.06095/): The article investigates the impact of smart contract protocols on market dynamics, focusing on their influence on price drift, trade size, and market depth in coupled markets.